Data co-processing method and system of linear servo actuator

Abstract

The invention provides a data co-processing method and system for a linear servo actuator. The method comprises the following steps: firstly, acquiring a multi-level temperature data set of a key heat source area in the linear servo actuator; performing dynamic coupling analysis processing on the multi-level temperature data set based on a thermal field prediction model to generate a temperature change trend prediction result; a dynamic heat dissipation strategy grade is matched according to the temperature change trend prediction result and real-time load current data, a heat dissipation execution control instruction is generated, and temperature feedback data in the heat dissipation process is monitored in real time; and based on a comparison result of the temperature feedback data and a preset temperature threshold, triggering a thermal failure protection mechanism to adjust the execution priority of the composite heat dissipation operation. According to the invention, power output can be reduced, external active heat dissipation control is triggered, equipment shutdown and other related instructions which are in effective contact with an abnormal working state can be triggered, so that the risk of equipment damage caused by abnormal operation of the actuator is effectively reduced, and the reliability and stability of the system are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of servo systems, in particular to a data collaborative processing method and system of a linear servo actuator. BACKGROUND

[0002] In the field of modern industrial automation and precision control, the running stability and reliability of linear servo actuators, as key motion control components, are of great importance. During the operation of a linear servo actuator, a large amount of heat is generated in the internal key heat source area (such as motor windings, power devices, etc.). If this heat cannot be effectively dissipated in time, the internal temperature of the actuator will rise sharply, which will affect its electrical performance, mechanical performance and service life.

[0003] At present, the heat dissipation treatment of linear servo actuators mainly relies on simple temperature monitoring and fixed mode heat dissipation control. However, this traditional method has many limitations. On the one hand, it does not fully consider the complex characteristics of the multi-level temperature distribution inside the actuator, and only uses the data of a single or limited number of temperature monitoring points for heat dissipation control, which cannot accurately reflect the real temperature conditions of the entire heat source area. On the other hand, the traditional heat dissipation strategy lacks the ability to predict temperature trends, and cannot dynamically adjust the heat dissipation measures according to the real-time load conditions and temperature changes of the actuator, resulting in low heat dissipation efficiency, and even in high temperature environments, it cannot take effective protective measures in time, increasing the risk of actuator thermal failure and affecting the normal operation of the entire system. Therefore, there is an urgent need for a more intelligent and efficient data collaborative processing method for linear servo actuators to solve the above problems in the prior art. SUMMARY

[0004] Therefore, the purpose of the embodiments of the present application is to provide a data collaborative processing method and system for a linear servo actuator.

[0005] According to one aspect of the embodiments of the present application, a data collaborative processing method for a linear servo actuator is provided, which comprises: obtaining a multi-level temperature data set of the internal key heat source area of the linear servo actuator, the multi-level temperature data set comprising a real-time heat source temperature sequence and a shell temperature distribution data; performing dynamic coupling analysis and processing on the multi-level temperature data set based on a heat field prediction model to generate a temperature trend prediction result; the heat field prediction model is obtained by associating historical temperature data and operating state parameters; matching a dynamic heat dissipation strategy level according to the temperature trend prediction result and real-time load current data to generate a heat dissipation control instruction; performing a composite heat dissipation operation corresponding to the heat dissipation control instruction and monitoring temperature feedback data in real time during the heat dissipation process; Based on a comparison result of the temperature feedback data and a preset temperature threshold, a thermal failure protection mechanism is triggered to adjust an execution priority of the composite heat dissipation operation.

[0006] According to another aspect of the embodiments of the present application, a data collaborative processing system of a linear servo actuator is provided, which comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory complete mutual communication through the communication bus; the memory is used for storing a computer program; and the processor is used for executing the computer program to realize the steps of the data collaborative processing method of the linear servo actuator according to any one of the above aspects.

[0007] According to another aspect of the embodiments of the present application, a readable storage medium is provided, which stores a computer program, and the computer program can execute the steps of the data collaborative processing method of the linear servo actuator when the computer program is run by a processor.

[0008] Through any one of the above aspects, by comprehensively acquiring a multi-level temperature data set of a key heat source area inside the linear servo actuator, real-time heat source temperature sequences and shell temperature distribution data are covered, and the temperature condition inside the actuator can be more accurately mastered. Based on dynamic coupling analysis and processing of the multi-level temperature data set by a thermal field prediction model, a temperature change trend prediction result is generated, the thermal field prediction model is trained based on the relevance of historical temperature data and running state parameters, and has accurate prediction ability for the temperature change trend. According to matching of the temperature change trend prediction result and real-time load current data, a dynamic heat dissipation strategy level is matched, and a heat dissipation control instruction is generated, so that dynamic adjustment of the heat dissipation strategy is realized, and the heat dissipation efficiency is greatly improved. The composite heat dissipation operation corresponding to the heat dissipation control instruction is executed, and temperature feedback data in the heat dissipation process is monitored in real time. Based on a comparison result of the temperature feedback data and a preset temperature threshold, a thermal failure protection mechanism is triggered to adjust an execution priority of the composite heat dissipation operation, further ensuring safe and stable operation of the actuator under various working conditions, effectively reducing the risk of thermal failure, prolonging the service life of the actuator, and improving the reliability and stability of the entire system.

[0009] In order to make the above-mentioned purposes, features and advantages of the embodiments of the present application more obvious and easy to understand, the following will be described in detail with reference to the embodiments and in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0010] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments. It should be understood that the following drawings only show some of the embodiments of the present application, and therefore should not be regarded as a limitation to the scope, and for those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0011] Figure 1 The component schematic diagram of the data collaborative processing system of the linear servo actuator provided by the embodiment of the present application is shown. Figure 2 The flow schematic diagram of the data collaborative processing method of the linear servo actuator provided by the embodiment of the present application is shown. DETAILED DESCRIPTION

[0012] In order to make the person in the art better understand the present application, the following will combine the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. According to the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of the present application.

[0013] The terms "first", "second", "third" and the like (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily have to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0014] Embodiment one: Figure 1An exemplary component diagram of a linear servo actuator's data co-processing system 100 is shown. The linear servo actuator's data co-processing system 100 can include one or more processors 104, such as one or more central processing units (CPUs), each of which can implement one or more hardware threads. The linear servo actuator's data co-processing system 100 can also include any storage media 106 for storing any kind of information, such as code, settings, data, etc. Without limitation, for example, the storage media 106 can include any one or combination of the following: any type of RAM, any type of ROM, a flash memory device, a hard disk, an optical disk, etc. More generally, any storage media can store information using any technology. Further, any storage media can provide volatile or non-volatile retention of information. Further, any storage media can represent a fixed or removable component of the linear servo actuator's data co-processing system 100. In one case, the linear servo actuator's data co-processing system 100 can perform any of the operations described in association with the relevant instructions being executed by the processor 104 and stored in any storage medium or combination of storage media. The linear servo actuator's data co-processing system 100 also includes one or more drive units 108, such as a hard disk drive unit, an optical disk drive unit, etc., for interacting with any storage media 106, as described above.

[0015] The linear servo actuator's data co-processing system 100 also includes an input / output 110 (I / O) for receiving various input (via input unit 112) and for providing various output (via output unit 114). One particular output mechanism can include a presentation device 116 and a presence-dependent graphical user interface (GUI) 118. The linear servo actuator's data co-processing system 100 can also include one or more network interfaces 120 for exchanging data with other devices via one or more communication units 122. One or more communication buses 124 couple the above-described components together.

[0016] The communication unit 122 can be implemented in any way, for example, through a local area network, a wide area network (e.g., the Internet), a point-to-point connection, etc., or any combination thereof. The communication unit 122 can include any combination of hardwired links, wireless links, routers, gateway functionality, name linear servo actuator's data co-processing system 100, etc., governed by any protocol or combination of protocols.

[0017] Embodiment Two: Figure 2 A flow diagram of a linear servo actuator's data co-processing method and system provided by an embodiment of the present invention is shown. The linear servo actuator's data co-processing method and system can be implemented by Figure 1The data collaborative processing system 100 of the linear servo actuator shown in the figure executes the detailed steps of the data collaborative processing method of the linear servo actuator as follows.

[0018] Step S110: Obtain a multi-level temperature data set of the internal key heat source area of the linear servo actuator, which includes a real-time heat source temperature sequence and shell temperature distribution data.

[0019] In this embodiment, the linear servo actuator works in the mechanical operation scene of industrial automation. In order to accurately grasp the temperature condition of the internal key heat source area, it is necessary to obtain a multi-level temperature data set. Specifically, this step includes the following sub-steps to realize effective data acquisition.

[0020] Step S111: A distributed temperature sensing unit is arranged on the surface of the key heat source of the linear servo actuator, and the real-time heat source temperature sequence is collected periodically.

[0021] In actual operation, the key heat sources of the linear servo actuator usually include motor windings, power modules and other parts. For motor windings, since they generate heat in the process of converting electrical energy into mechanical energy, they are one of the main heat sources. The power module also generates heat due to energy loss in the process of controlling current and voltage. On the surface of these key heat sources, a distributed temperature sensing unit is uniformly and reasonably arranged. Assuming that the motor windings are divided into three areas A, B and C, and the power module is divided into two areas D and E, a temperature sensing unit is installed in each area.

[0022] These temperature sensing units have high-precision temperature measurement capability and collect temperature data according to a preset period T. The collected data form a time sequence, i.e. a real-time heat source temperature sequence. For example, in the first period T, the temperature of area A of the motor winding is Ta1, the temperature of area B is Tb1, the temperature of area C is Tc1, the temperature of area D of the power module is Td1, and the temperature of area E is Te1; in the second period T, the temperatures of the corresponding areas are Ta2, Tb2, Tc2, Td2 and Te2, respectively, and so on. In this way, the real-time heat source temperature sequence contains temperature fluctuation data of multiple consecutive sampling periods, reflecting the change of the temperature of the key heat source with time.

[0023] Step S112: Obtain the shell temperature distribution data by scanning the surface of the shell of the linear servo actuator through an infrared thermal imaging unit; the shell temperature distribution data contains temperature gradient characteristics and hot spot migration trajectory.

[0024] Next, the shell surface of the linear servo actuator is scanned comprehensively using an infrared thermal imaging unit. The infrared thermal imaging unit can detect the infrared radiation intensity at different positions on the shell surface and convert it into corresponding temperature values using the principle of infrared radiation. During the scanning process, the shell surface is divided into multiple small areas, for example, divided into MxN grid areas.

[0025] For each grid area, the infrared thermal imaging unit measures its temperature value, thereby obtaining the temperature distribution of the entire shell surface. By analyzing these temperature values, temperature gradient features can be extracted. The temperature gradient refers to the change in temperature per unit distance. Assuming that the distance between two adjacent grid areas i and j is d, and the temperatures are Ti and Tj, respectively, the temperature gradient Gij between them is (Tj-Ti) / d. By calculating the temperature gradient at different positions, the direction and rate of heat transfer on the shell surface can be understood.

[0026] At the same time, during continuous multiple scanning processes, the position changes of the areas with higher temperatures (hot spots) are observed, thereby determining the migration trajectory of the hot spots. For example, in the first scan, the hot spot is located in the upper left corner of the shell surface; in the second scan, the hot spot moves to the upper right corner, and by recording the position change information of these hot spots, the migration trajectory of the hot spots can be obtained, which reflects the dynamic distribution of heat on the shell surface.

[0027] Step S113: Align the real-time heat source temperature sequence and the shell temperature distribution data by timestamp to generate the multi-level temperature data set.

[0028] Finally, since the real-time heat source temperature sequence and the shell temperature distribution data are obtained in different measurement methods, but are both time-related. In order to integrate these two kinds of data together to form a multi-level temperature data set, it is necessary to align them according to the timestamp. Assuming that the collection time points of the real-time heat source temperature sequence are t1, t2, t3……, and the scanning time points of the shell temperature distribution data are t1', t2', t3'……. By comparing the timestamps, the data at the same time point or similar time points are associated. For example, when t1 and t1' are similar, the real-time heat source temperature sequence data and the shell temperature distribution data at that time are combined together to form a complete data record. In this way, all the collected data are processed, and finally a multi-level temperature data set is generated, which integrates the temperature information of the internal key heat sources and the temperature distribution information of the shell surface.

[0029] Step S120: Based on the thermal field prediction model, the multi-level temperature data set is dynamically coupled and analyzed to generate a temperature change trend prediction result; the thermal field prediction model is trained by the correlation between historical temperature data and operating state parameters.

[0030] In this embodiment, after obtaining the multi-level temperature data set of the linear servo actuator, it is necessary to use the thermal field prediction model to deeply analyze these data to predict the trend of temperature change. The thermal field prediction model is trained based on the correlation between historical temperature data and operating state parameters, which can simulate the heat transfer process and temperature change law inside the linear servo actuator. The specific steps are as follows: Step S121: Extract the temperature fluctuation frequency feature and temperature peak value distribution feature in the real-time heat source temperature sequence.

[0031] For the real-time heat source temperature sequence, key feature information needs to be extracted. The temperature fluctuation frequency feature reflects the speed of temperature change over time. The temperature fluctuation frequency feature can be obtained by performing spectral analysis on the real-time heat source temperature sequence. Assuming that the real-time heat source temperature sequence is T(t), Fourier transform is performed on it to obtain the frequency spectrum function F(ω), where ω represents the frequency. By analyzing the frequency spectrum function F(ω), the main frequency component of temperature fluctuation can be determined. For example, in the frequency spectrum graph, find the frequency points with large amplitude, and the frequencies corresponding to these frequency points are the main frequencies of temperature fluctuation, which reflect the periodic characteristics of temperature change.

[0032] The temperature peak value distribution feature describes the distribution of peak values in the temperature sequence. The real-time heat source temperature sequence can be divided into multiple time periods, the temperature peaks in each time period are counted, and the size and position of these peaks are analyzed. For example, calculate the average, maximum, minimum and other statistical quantities of the temperature peak values in each time period, as well as the time distribution of the temperature peak values. Through these statistics and distribution, the distribution characteristics of the temperature peak values can be understood, which is very important for predicting extreme temperature changes.

[0033] Step S122: Analyze the heat diffusion rate feature and hot spot migration direction feature in the shell temperature distribution data.

[0034] For the shell temperature distribution data, the main analysis is the heat diffusion rate feature and the hot spot migration direction feature. The heat diffusion rate feature reflects the speed of heat transfer on the shell surface. The heat diffusion rate can be calculated by comparing the shell temperature distribution data at different time points. Assuming that the shell temperature distribution data T1(x, y) and T2(x, y) are obtained at time t1 and t2, respectively, where (x, y) represents the coordinates of the shell surface. For a point (x0, y0) on the shell surface, its temperature at time t1 and t2 is T1(x0, y0) and T2(x0, y0), respectively, and the heat diffusion rate of the point is v=(T2(x0, y0)-T1(x0, y0)) / (t2-t1). By calculating the heat diffusion rates of multiple points on the shell surface and performing statistical analysis, the heat diffusion rate feature of the entire shell surface can be obtained.

[0035] The hotspot migration direction feature describes the direction of the hotspot moving on the surface of the shell. By observing the position changes of the hotspot in the temperature distribution data obtained from multiple consecutive scans, the direction of the hotspot migration can be determined. For example, the hotspot is located at point (x1, y1) in the first scan, and the hotspot moves to point (x2, y2) in the second scan. The direction of the hotspot migration can be represented by the vector (x2-x1, y2-y1). By analyzing the position changes of the hotspot at multiple time points, the direction rule of the hotspot migration is summarized, which is very helpful for understanding the transmission path and trend of heat on the surface of the shell.

[0036] Step S123: input the temperature fluctuation frequency feature, the temperature peak value distribution feature, the heat diffusion rate feature, and the hotspot migration direction feature into the thermal field prediction model.

[0037] After extracting and analyzing the above features, the temperature fluctuation frequency feature, the temperature peak value distribution feature, the heat diffusion rate feature, and the hotspot migration direction feature are input into the thermal field prediction model as input data. The thermal field prediction model is a trained model that can simulate the heat transfer process and temperature change inside the linear servo actuator according to these input features.

[0038] Step S124: call the thermal field prediction model to model the thermal-mechanical-electrical coupling relationship of the input features, and generate a temperature change trend prediction result in the target time period; wherein the thermal field prediction model is iteratively trained through the time sequence correlation of historical temperature data, load current, motion frequency, and environmental parameters, and the length of the target time period is dynamically adjusted according to the fluctuation amplitude of the current load.

[0039] After receiving the input features, the thermal field prediction model will model the thermal-mechanical-electrical coupling relationship inside the linear servo actuator. The thermal-mechanical-electrical coupling relationship refers to the mutual influence relationship between thermal phenomena, mechanical motion, and electrical signals during the operation of the linear servo actuator. For example, the change of the load current will affect the heating of the motor, and then affect the temperature distribution; the change of the temperature will affect the performance of the motor and the mechanical motion.

[0040] The thermal field prediction model will simulate and predict this coupling relationship according to the time sequence correlation of historical temperature data, load current, motion frequency, and environmental parameters. In the training process, a large amount of historical data is used to continuously adjust the parameters of the thermal field prediction model through iterative training, so that the thermal field prediction model can accurately reflect the thermal-mechanical-electrical coupling relationship.

[0041] The length of the target time period is dynamically adjusted according to the fluctuation amplitude of the current load current. When the fluctuation amplitude of the load current is large, it indicates that the running state of the linear servo actuator changes greatly, and the temperature change may also be relatively intense, so the target time period is set to be relatively short, so as to more accurately predict the temperature change trend; when the fluctuation amplitude of the load current is small, it indicates that the running state is relatively stable, and the temperature change is relatively slow, so the target time period can be set to be relatively long. For example, by establishing a mapping relationship between the fluctuation amplitude of the load current and the length of the target time period, according to the real-time measured fluctuation amplitude of the load current, the corresponding length of the target time period is found from the mapping relationship, and then the thermal field prediction model predicts the temperature change trend in the target time period to generate the corresponding prediction result.

[0042] Step S130: dynamically matching the heat dissipation strategy level according to the temperature change trend prediction result and the real-time load current data, and generating a heat dissipation control instruction.

[0043] In this embodiment, after obtaining the temperature change trend prediction result, it is necessary to combine the real-time load current data to match the appropriate dynamic heat dissipation strategy level, and generate the corresponding heat dissipation control instruction, so as to ensure that the temperature of the linear servo actuator is within the safe range. The specific steps are as follows: Step S131: identifying the temperature rise rate feature and the predicted temperature peak value in the temperature change trend prediction result.

[0044] For the temperature change trend prediction result, it is necessary to extract the key feature information therefrom. The temperature rise rate feature reflects the speed of temperature rise with time. The temperature rise rate can be obtained by performing a derivative operation on the temperature change trend prediction result. Assuming that the temperature change trend prediction result is T(t), the derivative thereof is a temperature rise rate function v(t)=dT(t) / dt. By analyzing the temperature rise rate function v(t), the speed of temperature rise can be determined, for example, the temperature rise rate is large in a certain time period, indicating that the temperature rise is fast.

[0045] The predicted temperature peak value is the highest temperature value in the temperature change trend prediction result. In the temperature change trend prediction result, by comparing the temperature values at different time points, the maximum value is found, which is the predicted temperature peak value. The predicted temperature peak value is very important for judging whether the linear servo actuator will exceed the safe temperature range.

[0046] Step S132: determining the initial heat dissipation strategy level according to the difference between the predicted temperature peak value and the first temperature threshold.

[0047] The first temperature threshold is a pre-set safety temperature limit for determining whether the temperature of the linear servo actuator is within a safety range. The predicted temperature peak value is compared with the first temperature threshold, and a difference ΔT=Tpeak-Tthreshold1 is calculated, where Tpeak is the predicted temperature peak value and Tthreshold1 is the first temperature threshold. According to the size of the difference ΔT, the initial heat dissipation strategy level is determined. For example, when ΔT is small, it indicates that the predicted temperature peak value is close to the first temperature threshold, and a lower level of heat dissipation strategy can be selected at this time; when ΔT is large, it indicates that the predicted temperature peak value is much higher than the first temperature threshold, and a higher level of heat dissipation strategy needs to be selected. A mapping relationship between the difference ΔT and the initial heat dissipation strategy level can be established, and the corresponding initial heat dissipation strategy level is found from the mapping relationship according to the calculated difference ΔT.

[0048] Step S133: correcting the initial heat dissipation strategy level based on the fluctuation amplitude of the real-time load current data to obtain a target heat dissipation strategy level.

[0049] The fluctuation amplitude of the real-time load current data reflects the change of the running state of the linear servo actuator. When the fluctuation amplitude of the load current is large, it indicates that the running state of the linear servo actuator is unstable, and more heat may be generated, so the heat dissipation needs to be strengthened; when the fluctuation amplitude of the load current is small, it indicates that the running state is relatively stable, and the heat dissipation demand is relatively low.

[0050] According to the fluctuation amplitude of the real-time load current data, the initial heat dissipation strategy level is corrected. For example, a mapping relationship between the fluctuation amplitude of the load current and the correction coefficient of the heat dissipation strategy level is established, and the corresponding correction coefficient k is found from the mapping relationship according to the real-time measured fluctuation amplitude of the load current. Then the initial heat dissipation strategy level is multiplied by the correction coefficient k to obtain the target heat dissipation strategy level. If k is greater than 1, it indicates that the heat dissipation strategy level needs to be improved; if k is less than 1, it indicates that the heat dissipation strategy level can be reduced.

[0051] Step S134: activating a corresponding composite heat dissipation operation according to the target heat dissipation strategy level to generate a heat dissipation control instruction containing operation timing and power parameters; wherein the composite heat dissipation operation includes a passive heat dissipation stage, an active convection enhancement stage and a power adjustment stage, and the switching conditions of each stage are dynamically set based on the temperature rise rate characteristics.

[0052] After the target heat dissipation strategy level is determined, the corresponding composite heat dissipation operation is activated according to the level. The composite heat dissipation operation includes a passive heat dissipation stage, an active convection enhancement stage and a power adjustment stage.

[0053] In the passive heat dissipation stage, the main heat dissipation operation is performed by the metal heat dissipation unit, such as dissipating heat through metal heat dissipation fins. When the temperature rise rate is slow, it is usually in the passive heat dissipation stage.

[0054] When the temperature rise rate accelerates and the first temperature feedback data exceeds the second temperature threshold, switch to the active convection enhancement stage. In the active convection enhancement stage, the vortex fan unit is started to increase the heat dissipation efficiency by increasing air convection.

[0055] If the second temperature feedback data does not reach the expected cooling rate in the active convection enhancement stage, the power adjustment stage is triggered. In the power adjustment stage, the load current is reduced and the semiconductor refrigeration unit is activated to further reduce the temperature.

[0056] The switching conditions of each stage are dynamically set based on the temperature rise rate characteristics. For example, when the temperature rise rate exceeds a certain set value, switch from the passive heat dissipation stage to the active convection enhancement stage; when the cooling effect of the active convection enhancement stage is not obvious, trigger the power adjustment stage.

[0057] According to the target heat dissipation strategy level and the switching conditions of each stage, generate heat dissipation control instructions containing operation timing and power parameters. The operation timing specifies the start time and duration of each heat dissipation stage, and the power parameters determine the operating power of each heat dissipation device (such as the vortex fan unit and the semiconductor refrigeration unit).

[0058] Step S140: Perform the corresponding composite heat dissipation operation of the heat dissipation control instruction, and monitor the temperature feedback data in real time during the heat dissipation process.

[0059] In this embodiment, after generating the heat dissipation control instruction, the corresponding composite heat dissipation operation needs to be performed, and the temperature feedback data in the heat dissipation process needs to be monitored in real time to evaluate the heat dissipation effect. The specific steps are as follows: Step S141: In the passive heat dissipation stage, control the metal heat dissipation unit to perform the basic heat dissipation operation, and collect the first temperature feedback data.

[0060] In the passive heat dissipation stage, according to the heat dissipation control instruction, control the metal heat dissipation unit to perform the basic heat dissipation operation. The metal heat dissipation unit is usually composed of metal heat dissipation fins, which utilize the good heat conduction performance of metal to dissipate the heat generated by the linear servo actuator. During the heat dissipation process, the first temperature feedback data is collected through temperature sensing units distributed at key positions, which reflect the temperature change of the linear servo actuator in the passive heat dissipation stage.

[0061] Step S142: When the first temperature feedback data exceeds the second temperature threshold, switch to the active convection enhancement stage, start the vortex fan unit and collect the second temperature feedback data.

[0062] Real-time monitoring of the first temperature feedback data, when the first temperature feedback data exceeds the second temperature threshold, indicating that the passive heat dissipation stage is not effective, and needs to switch to the active convection enhancement stage. At this time, according to the heat dissipation control instruction, the vortex fan unit is started, and the vortex fan unit enhances the heat dissipation by accelerating the air flow. In the active convection enhancement stage, the second temperature feedback data is continuously collected by the temperature sensing unit, which reflects the temperature change of the linear servo actuator in the active convection enhancement stage.

[0063] Step S143: If the second temperature feedback data does not reach the expected cooling rate, trigger the power adjustment stage, reduce the load current and activate the semiconductor refrigeration unit, and collect the third temperature feedback data.

[0064] The expected cooling rate is dynamically calculated according to the temperature drop curve corresponding to the target heat dissipation strategy level. Compare the cooling rate of the second temperature feedback data with the expected cooling rate, if the second temperature feedback data does not reach the expected cooling rate, indicating that the heat dissipation effect of the active convection enhancement stage is still not ideal, and the power adjustment stage needs to be triggered. In the power adjustment stage, according to the heat dissipation control instruction, the load current is reduced, the heat generation of the linear servo actuator is reduced, and the semiconductor refrigeration unit is activated to further reduce the temperature. In the power adjustment stage, the third temperature feedback data is continuously collected by the temperature sensing unit, which reflects the temperature change of the linear servo actuator in the power adjustment stage.

[0065] Step S144: The first temperature feedback data, the second temperature feedback data and the third temperature feedback data are marked by stage and stored as a heat dissipation process log.

[0066] The collected first temperature feedback data, second temperature feedback data and third temperature feedback data are marked according to the passive heat dissipation stage, active convection enhancement stage and power adjustment stage, and then these data are stored as a heat dissipation process log. The heat dissipation process log records the temperature change of the linear servo actuator in the entire heat dissipation process, providing data support for subsequent analysis and optimization.

[0067] Step S150: Based on the comparison result of the temperature feedback data and the preset temperature threshold, trigger the thermal failure protection mechanism to adjust the execution priority of the composite heat dissipation operation.

[0068] In this embodiment, after the composite heat dissipation operation is executed and the temperature feedback data is collected, the thermal failure protection mechanism needs to be triggered according to the comparison result of the temperature feedback data and the preset temperature threshold, and the execution priority of the composite heat dissipation operation is adjusted to ensure the safe operation of the linear servo actuator. The specific steps are as follows: Step S151: Analyze the temperature change slope feature and hotspot migration path feature of each stage in the heat dissipation process log.

[0069] The temperature feedback data of each stage recorded in the heat dissipation process log is analyzed to extract the temperature change slope feature and hotspot migration path feature. The temperature change slope feature reflects the speed of temperature change over time, which can be obtained by performing a derivative operation on the temperature feedback data. For example, for the temperature feedback data T1(t) of the passive heat dissipation stage, the derivative operation obtains the temperature change slope function v1(t)=dT1(t) / dt; for the temperature feedback data T2(t) of the active convection enhancement stage, the derivative operation obtains the temperature change slope function v2(t)=dT2(t) / dt; for the temperature feedback data T3(t) of the power adjustment stage, the derivative operation obtains the temperature change slope function v3(t)=dT3(t) / dt. By analyzing these temperature change slope functions, the speed of temperature change in each stage can be understood.

[0070] The hotspot migration path feature describes the movement path of the hotspot during the heat dissipation process. By observing the temperature distribution data at different time points in the heat dissipation process log, the position change of the hotspot in each stage is determined, and the hotspot migration path is obtained. By analyzing the hotspot migration path, the direction of heat transfer and the concentration area during the heat dissipation process can be understood.

[0071] Step S152: Trigger the priority reassignment operation when the temperature change slope feature does not match the preset safety model.

[0072] The preset safety model is a model established according to the normal operating state of the linear servo actuator and the heat dissipation requirements, which specifies the normal range of temperature change slope in each stage. The temperature change slope feature obtained by analysis is compared with the preset safety model. If it is found that the temperature change slope feature exceeds the range specified by the preset safety model, it indicates that the temperature change of the linear servo actuator is abnormal, and there may be a risk of thermal failure. At this time, the priority reassignment operation is triggered.

[0073] Specifically, this step further includes the following sub-steps: Step S1521: Identify the abnormal fluctuation pattern of the temperature feedback data in the current heat dissipation stage.

[0074] For the temperature feedback data of the current heat dissipation stage, the fluctuation situation is analyzed, and abnormal fluctuation patterns are identified. The abnormal fluctuation patterns include temperature sudden rise interval characteristics, hot spot migration speed mutation characteristics, and heat dissipation response delay characteristics. The temperature sudden rise interval characteristic is the time interval of the sudden rise of the temperature in a short time. By analyzing the time point of the sudden rise of the temperature in the temperature feedback data, the time interval of the adjacent two temperature sudden rises is calculated, and the temperature sudden rise interval characteristic is obtained. The hot spot migration speed mutation characteristic is the case that the speed of the hot spot suddenly changes during the migration process. By comparing the distance and time of the hot spot migration in different time periods, the hot spot migration speed is calculated, and when the speed change exceeds the set threshold, it is considered that the hot spot migration speed mutation characteristic appears. The heat dissipation response delay characteristic is the case that the temperature does not decrease in time after starting the heat dissipation device. By analyzing the change of the temperature feedback data after starting the heat dissipation device, it is judged whether there is a heat dissipation response delay.

[0075] Step S1522: match the abnormal fluctuation pattern with the feature library of historical failure events to determine the potential thermal failure risk level.

[0076] A feature library of historical failure events is established, which records the temperature fluctuation patterns and hot spot migration conditions and other characteristic information when thermal failure faults occur in the past. The identified abnormal fluctuation pattern is matched with the feature library of historical failure events, and the similarity between the two is calculated to judge the similarity between the current abnormal fluctuation pattern and the historical failure events. According to the size of the similarity, the potential thermal failure risk level is determined. For example, if the similarity is high, it is considered that the potential thermal failure risk level is high; if the similarity is low, it is considered that the potential thermal failure risk level is low.

[0077] Step S1523: adjust the duration proportion of each stage in the composite heat dissipation operation according to the potential thermal failure risk level.

[0078] According to the determined potential thermal failure risk level, the duration proportions of the passive heat dissipation stage, the active convection enhancement stage and the power adjustment stage in the composite heat dissipation operation are adjusted. When the potential thermal failure risk level is high, the duration proportion of the power adjustment stage is increased, and the duration proportions of the passive heat dissipation stage and the active convection enhancement stage are reduced, so as to reduce the temperature faster and avoid the occurrence of thermal failure; when the potential thermal failure risk level is low, the duration proportion of the passive heat dissipation stage can be appropriately increased, and the duration proportion of the power adjustment stage is reduced, so as to save energy.

[0079] Step S1524: re-distribute the heat dissipation resources to the high-risk area under the adjusted duration proportion.

[0080] According to the adjusted proportion of the duration of each stage, the heat dissipation resources are redistributed. The high-risk area refers to an area with higher temperature and greater heat dissipation demand determined according to the characteristics of the hotspot migration path and the temperature change slope. For example, for a vortex fan unit, its wind direction and speed can be adjusted to blow more towards the high-risk area; for a semiconductor refrigeration unit, its refrigeration position can be adjusted to focus on refrigeration in the high-risk area. By redistributing the heat dissipation resources, the heat dissipation efficiency is improved and the risk of thermal failure is reduced.

[0081] Step S153: Adjust the working area of the semiconductor refrigeration unit according to the hotspot migration path characteristics, and increase the execution weight of the power adjustment stage.

[0082] According to the characteristics of the hotspot migration path, the direction of heat transfer and the concentration area in the heat dissipation process are understood, and the working area of the semiconductor refrigeration unit is adjusted. The refrigeration position of the semiconductor refrigeration unit is adjusted to the area where the hotspots are located, so that it can more effectively reduce the temperature of the hotspot area. At the same time, the execution weight of the power adjustment stage is increased, and when the temperature feedback data is abnormal, the power adjustment stage is triggered faster to reduce the load current and activate the semiconductor refrigeration unit to enhance the heat dissipation effect.

[0083] Step S154: In the priority redistribution process, if the local temperature is monitored to exceed the third temperature threshold, the shape memory alloy contact is activated to shunt the load current.

[0084] In the priority redistribution process, the temperature of each part of the linear servo actuator is continuously monitored. When the local temperature is monitored to exceed the third temperature threshold, it indicates that the temperature of this area is too high and may cause damage to the equipment, so the shape memory alloy contact is activated to shunt the load current. The specific operation is as follows: Step S1541: Monitor the real-time temperature distribution and current density distribution of the key heat source area.

[0085] Through the temperature sensing unit and current sensing unit distributed in the key heat source area, the temperature distribution and current density distribution of the key heat source area are monitored in real time. The temperature distribution reflects the temperature of each part of the key heat source area, and the current density distribution reflects the distribution of the current in the key heat source area.

[0086] Step S1542: When the temperature of a specific area is detected to exceed the phase transition threshold, the shape memory alloy contact at the corresponding position is triggered to close.

[0087] The shape memory alloy contact has special physical properties, and when the temperature reaches the phase transition threshold, its shape will change, thereby realizing the closure of the contact. According to the real-time monitored temperature distribution, when the temperature of a specific area is detected to exceed the phase transition threshold, the shape memory alloy contact at the corresponding position of the area is triggered to close.

[0088] Step S1543: Direct part of the load current to the backup circuit path through the closed contact.

[0089] When the shape memory alloy contact is closed, part of the load current will flow to the backup circuit path through the closed contact, thereby reducing the current load in the critical heat source area and reducing the amount of heat generated.

[0090] Step S1544: Real-time calculation of the heat source temperature change rate and current balance degree after shunting.

[0091] After shunting the load current, the temperature change of the critical heat source area is monitored in real time, and the heat source temperature change rate is calculated. The heat source temperature change rate reflects the speed of temperature drop in the critical heat source area after shunting. At the same time, the current of the backup circuit path and the original circuit path is monitored, and the current balance degree is calculated. The current balance degree reflects the uniformity of the distribution of the current in different circuit paths after shunting.

[0092] Step S1545: If the heat source temperature change rate does not reach the expected value, gradually increase the shunting ratio until the temperature is stable.

[0093] Compare the calculated heat source temperature change rate with the expected value. If the heat source temperature change rate does not reach the expected value, it means that the shunting effect is not good, and the shunting ratio needs to be gradually increased. By adjusting the conduction degree of the shape memory alloy contact, the current ratio flowing to the backup circuit path is gradually increased, until the temperature of the critical heat source area is stable within a safe range. Among them, the phase transition threshold is dynamically calibrated according to the material characteristics and historical thermal failure data. Through the analysis of historical thermal failure data, the phase transition of different materials under different working conditions is understood, and the phase transition threshold is dynamically adjusted combined with the current operating environment and equipment state, to ensure that the shape memory alloy contact can accurately trigger when the temperature is too high.

[0094] Step S155: Recalculate the target heat dissipation strategy level according to the current distribution after shunting, and update the operation timing of the heat dissipation control instruction.

[0095] Step S1551: Obtain the load current distribution data after shunting and the updated temperature feedback data.

[0096] After shunting the load current, the load current distribution data after shunting is obtained through the current sensing unit to understand the distribution of the current in different circuit paths. At the same time, the updated temperature feedback data is obtained through the temperature sensing unit to understand the temperature change of each part of the linear servo actuator after shunting.

[0097] Step S1552: Regenerate the corrected temperature change trend prediction result based on the updated heat field prediction model.

[0098] The updated temperature feedback data and the shunted load current distribution data are used to update the thermal field prediction model. The thermal field prediction model will re-learn the heat transfer process and temperature variation law inside the linear servo actuator according to the new data. Then, the updated temperature feedback data and the shunted load current distribution data are input into the updated thermal field prediction model to regenerate the corrected temperature variation trend prediction result.

[0099] Step S1553: According to the matching of the corrected temperature variation trend prediction result and the shunted load current data, a new heat dissipation strategy level is matched.

[0100] Similar to the previous method of matching the heat dissipation strategy level, the temperature rise rate feature and the predicted temperature peak value are extracted from the corrected temperature variation trend prediction result, the initial heat dissipation strategy level is determined according to the difference between the predicted temperature peak value and the first temperature threshold, and the initial heat dissipation strategy level is corrected based on the fluctuation amplitude of the shunted load current data to obtain the new heat dissipation strategy level.

[0101] Step S1554: The execution difference between the new and old heat dissipation strategy levels is compared, and the generation logic of the heat dissipation control instruction is optimized.

[0102] This step further includes the following sub-steps: Step S1554-1: Extract operation effect data under the same load condition in the historical heat dissipation process.

[0103] From the historical heat dissipation process log, the heat dissipation process records under the same load condition as the current shunted load current condition are filtered out, and the operation effect data in these records, such as temperature drop rate, running power of heat dissipation equipment, etc., are extracted.

[0104] Step S1554-2: Establish a correlation analysis model of heat dissipation strategy level and temperature stabilization time.

[0105] Using the extracted operation effect data, a correlation analysis model of heat dissipation strategy level and temperature stabilization time is established. This model can be trained by machine learning algorithm to find the relationship between heat dissipation strategy level and temperature stabilization time.

[0106] Step S1554-3: According to the correlation analysis model, the matching weight coefficient of the heat dissipation strategy level is corrected.

[0107] According to the results of the correlation analysis model, the matching weight coefficient of the heat dissipation strategy level is corrected. If a certain heat dissipation strategy level can make the temperature stabilize faster under the same load condition, the matching weight coefficient of this heat dissipation strategy level is increased; otherwise, the matching weight coefficient of this heat dissipation strategy level is decreased.

[0108] Step S1554-4: When generating a new heat dissipation control instruction, introduce the priority of adjusting the operation timing sequence.

[0109] When generating a new heat dissipation control instruction, adjust the priority of the operation timing sequence according to the modified matching weight coefficient. For example, for the heat dissipation operation corresponding to the heat dissipation strategy level with a higher weight coefficient, the start time is advanced or the duration is increased.

[0110] Step S1554-5: Map the adjusted priority to the heat dissipation resource allocation strategy to form a closed-loop optimization mechanism.

[0111] Map the adjusted operation timing priority to the heat dissipation resource allocation strategy, and reasonably allocate the operating power and working time of the heat dissipation device according to the priority. At the same time, continuously monitor the temperature feedback data in the heat dissipation process, and further adjust the heat dissipation strategy level and the heat dissipation control instruction according to the temperature change, forming a closed-loop optimization mechanism to continuously improve the heat dissipation effect and the reliability of the device.

[0112] The construction and training of the thermal field prediction model are described as follows.

[0113] First, collect historical temperature data, load current data, motion frequency data, and environmental parameter data of the linear servo actuator. The historical temperature data includes the temperature data of the internal key heat source area and the shell temperature distribution data, the load current data records the current size at different time periods, the motion frequency data reflects the motion speed of the linear servo actuator, and the environmental parameter data such as environmental temperature, humidity, etc.

[0114] Then, pre-process the collected historical temperature data, load current data, motion frequency data, and environmental parameter data, including data cleaning, normalization, and feature extraction. Data cleaning is to remove noise and outliers in historical data to ensure data accuracy. Normalization is to convert different dimensional data to the same scale range, such as normalizing temperature data, current data, etc. to the interval of 0 to 1 to ensure the stability of model training. Feature extraction is to extract useful features from historical data, such as temperature fluctuation frequency features, temperature peak distribution features, heat diffusion rate features, etc.

[0115] The thermal field prediction model adopts a multi-layer neural network architecture, including an input layer, a hidden layer, and an output layer. The input layer receives pre-processed data features, the hidden layer consists of multiple neurons, which are used for non-linear transformation and feature extraction of input features, and the output layer outputs temperature change trend prediction results. The number of neurons and the number of layers in the hidden layer are adjusted according to actual conditions to achieve the best prediction effect.

[0116] The historical data after preprocessing is used to train the thermal field prediction model. During the training process, the back propagation algorithm is used to adjust the parameters of the model, so that the output results of the model are as close as possible to the actual temperature change trend. The training parameters include learning rate, training rounds, etc. The learning rate controls the step size of the model parameter update, and the training rounds determine the number of model training. By continuously adjusting the training parameters, the prediction accuracy of the model is improved.

[0117] The trained thermal field prediction model is evaluated using the validation data set. The evaluation indicators include mean square error, mean absolute error, etc. If the evaluation result is not ideal, the model is optimized, such as adjusting the model architecture, increasing the training data or adjusting the training parameters, etc., until the prediction performance of the model meets the requirements.

[0118] In the embodiment, the internal key data of the linear servo actuator is first obtained, including a multi-level temperature data set of a heat source area, real-time running status and early warning monitoring of the device (whether there is an error or alarm), real-time motion data of the device (motor end speed, end speed, end running position, motor rotation position, following error, etc.), and then the corresponding real-time heat source temperature sequence and shell temperature distribution data are obtained after comprehensive fusion. Then, the thermal field prediction model trained by the correlation between historical temperature data and running state parameters is used to dynamically couple and analyze the multiple key data sets to generate state prediction results such as temperature change trend, so as to realize the device state early warning effect. Then, according to the prediction result and real-time load current data, a dynamic heat dissipation strategy level is matched to generate related instructions including reducing power output, triggering external active heat dissipation control, device shutdown, etc. to effectively reduce the risk of device damage caused by abnormal operation of the actuator, and improve the system reliability and stability.

[0119] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described system, device and unit can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0120] It is obvious to those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and can be implemented in other specific forms without departing from the spirit or essential characteristics of the present application. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting, and the scope of the present application is defined by the appended claims rather than the above description, and therefore all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be included in the present application.

Claims

1. A data collaborative processing method for a linear servo actuator, characterized in that, The method includes: A multi-level temperature data set of key heat source areas inside a linear servo actuator is obtained, the multi-level temperature data set including real-time heat source temperature sequence and shell temperature distribution data; The multi-level temperature data set is dynamically coupled and analyzed based on the thermal field prediction model to generate temperature change trend prediction results; the thermal field prediction model is obtained by training on the correlation between historical temperature data and operating status parameters. Based on the predicted temperature change trend and the real-time load current data, a dynamic heat dissipation strategy level is matched to generate a heat dissipation control command. Execute the composite heat dissipation operation corresponding to the heat dissipation control command, and monitor the temperature feedback data in real time during the heat dissipation process; Based on the comparison between the temperature feedback data and the preset temperature threshold, a thermal failure protection mechanism is triggered to adjust the execution priority of the composite heat dissipation operation.

2. The data collaborative processing method according to claim 1, characterized in that, The acquisition of multi-level temperature data sets for key heat source regions inside the linear servo actuator includes: Distributed temperature sensing units are installed on the key heat source surface of the linear servo actuator to periodically collect the real-time heat source temperature sequence; The surface of the linear servo actuator housing is scanned by an infrared thermal imaging unit to obtain housing temperature distribution data; the housing temperature distribution data includes temperature gradient characteristics and hot spot migration trajectories. The real-time heat source temperature sequence is aligned with the shell temperature distribution data by timestamp to generate the multi-level temperature data set. The real-time heat source temperature sequence includes temperature fluctuation data from multiple consecutive sampling periods, and the shell temperature distribution data includes the spatial distribution characteristics of the heat conduction path.

3. The data collaborative processing method according to claim 1, characterized in that, The dynamic coupling analysis of the multi-level temperature data set based on the thermal field prediction model to generate temperature change trend prediction results includes: Extract the temperature fluctuation frequency characteristics and temperature peak distribution characteristics from the real-time heat source temperature sequence; Analyze the characteristics of thermal diffusion rate and hot spot migration direction in the shell temperature distribution data; The temperature fluctuation frequency characteristics, the temperature peak distribution characteristics, the heat diffusion rate characteristics, and the hot spot migration direction characteristics are input into the thermal field prediction model; The thermal field prediction model is invoked to model the thermo-mechanical-electrical coupling relationship of the input features, and the temperature change trend prediction result within the target time period is generated. The thermal field prediction model is iteratively trained by the temporal correlation between historical temperature data and load current, motion frequency, and environmental parameters. The duration of the target time period is dynamically adjusted according to the fluctuation range of the current load current.

4. The data collaborative processing method according to claim 1, characterized in that, The step of matching the dynamic heat dissipation strategy level based on the temperature change trend prediction result and the real-time load current data to generate heat dissipation control instructions includes: Identify the temperature rise rate characteristics and predicted temperature peak value in the temperature change trend prediction results; The initial heat dissipation strategy level is determined based on the difference between the predicted peak temperature and the first temperature threshold. The initial heat dissipation strategy level is corrected based on the fluctuation range of the real-time load current data to obtain the target heat dissipation strategy level; Activate the corresponding composite heat dissipation operation according to the target heat dissipation strategy level, and generate a heat dissipation control command containing operation timing and power parameters; The composite heat dissipation operation includes a passive heat dissipation stage, an active convection enhancement stage, and a power adjustment stage, with the switching conditions for each stage dynamically set based on the temperature rise rate characteristics.

5. The data collaborative processing method according to claim 4, characterized in that, The execution of the composite heat dissipation operation corresponding to the heat dissipation control command, and the real-time monitoring of temperature feedback data during the heat dissipation process, includes: During the passive cooling phase, the metal heat sink unit is controlled to perform basic cooling operations and the first temperature feedback data is collected. When the first temperature feedback data exceeds the second temperature threshold, switch to the active convection enhancement stage, start the vortex fan unit and collect the second temperature feedback data; If the second temperature feedback data does not reach the expected cooling rate, the power adjustment stage is triggered, the load current is reduced and the semiconductor cooling unit is activated to collect the third temperature feedback data. The first temperature feedback data, the second temperature feedback data, and the third temperature feedback data are stored as a heat dissipation process log after being marked by stages. The expected cooling rate is dynamically calculated based on the temperature drop curve corresponding to the target heat dissipation strategy level.

6. The data collaborative processing method according to claim 5, characterized in that, The step of triggering a thermal failure protection mechanism based on the comparison result between the temperature feedback data and a preset temperature threshold to adjust the execution priority of the composite heat dissipation operation includes: Analyze the temperature change slope characteristics and hotspot migration path characteristics of each stage in the heat dissipation process log; When the temperature change slope characteristic is detected to be mismatched with the preset safety model, a priority reassignment operation is triggered; Adjust the working area of ​​the semiconductor cooling unit according to the characteristics of the hotspot migration path, and increase the execution weight of the power adjustment stage; During the priority redistribution process, if the local temperature is detected to exceed the third temperature threshold, the shape memory alloy contacts are activated to shunt the load current. The target heat dissipation strategy level is recalculated based on the current distribution after the current is diverted, and the operation timing of the heat dissipation control command is updated.

7. The data collaborative processing method according to claim 6, characterized in that, When the temperature change slope feature is detected to be mismatched with the preset safety model, a priority reallocation operation is triggered, including: Identify abnormal fluctuation patterns in temperature feedback data during the current heat dissipation phase; The abnormal fluctuation pattern is matched with the feature library of historical failure events to determine the potential thermal failure risk level; The duration ratio of each stage in the composite heat dissipation operation is adjusted according to the potential thermal failure risk level. Under the adjusted duration ratio, heat dissipation resources are reallocated to high-risk areas; The abnormal fluctuation patterns include temperature surge interval characteristics, hot spot migration speed abrupt change characteristics, and heat dissipation response delay characteristics.

8. The data collaborative processing method according to claim 7, characterized in that, The activation of the shape memory alloy contact to shunt load current includes: Monitor the real-time temperature and current density distribution in key heat source areas; When the temperature in a specific area exceeds the phase transition threshold, the shape memory alloy contact at the corresponding location is triggered to close. By closing the contacts, a portion of the load current is diverted to the backup circuit path. Real-time calculation of the rate of change of heat source temperature and current balance after the split; If the rate of change of the heat source temperature does not reach the expected value, the diversion ratio is gradually increased until the temperature stabilizes. The phase transition threshold is dynamically calibrated based on material properties and historical thermal failure data.

9. The data collaborative processing method according to claim 8, characterized in that, The step of recalculating the target heat dissipation strategy level based on the current distribution after shunting includes: Acquire the load current distribution data after shunting and the updated temperature feedback data; The corrected temperature change trend prediction results are regenerated based on the updated thermal field prediction model; A new heat dissipation strategy level is matched based on the predicted results of the corrected temperature change trend and the load current data after current diversion. By comparing the execution differences between the old and new heat dissipation strategy levels, the generation logic of heat dissipation control commands was optimized. The optimized generation logic will be applied to operational decisions in the subsequent heat dissipation stage. The step of comparing the execution differences between the old and new heat dissipation strategy levels and optimizing the generation logic of heat dissipation control commands includes: Extract operational performance data under the same load conditions during historical heat dissipation processes; Establish a correlation analysis model between heat dissipation strategy level and temperature stabilization time; The matching weight coefficients of the heat dissipation strategy level are adjusted based on the correlation analysis model. When generating new heat dissipation control commands, a weighting coefficient is introduced to adjust the priority of the operation timing; The adjusted priorities are mapped to the heat dissipation resource allocation strategy, forming a closed-loop optimization mechanism.

10. A data collaborative processing system for a linear servo actuator, characterized in that, include: The processor, communication interface, memory, and communication bus are provided, wherein the processor, communication interface, and memory communicate with each other via the communication bus. The memory is used to store computer programs; the processor is used to execute the computer programs to implement the data collaborative processing method steps of the linear servo actuator according to any one of claims 1-9.

Images