Rotor core heat treatment process optimization method and system based on temperature field monitoring
By using temperature field monitoring and multi-channel optimization, the problem of inaccurate temperature control in the heat treatment of stator and rotor cores was solved, and the stability and consistency of core quality were achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- NANTONG SHUANGYAO PRESSING CO LTD
- Filing Date
- 2025-10-13
- Publication Date
- 2026-04-21
AI Technical Summary
In the existing technology, the temperature control during the heat treatment of stator and rotor cores is not precise and the uniformity is poor, resulting in unstable core quality and difficulty in ensuring the consistency of batch products.
By extracting samples from the stator and rotor cores of the target batch, monitoring the temperature field, determining the location of key temperature monitoring anchor points, splitting the temperature transmission channels, and optimizing the heat treatment process parameters, multi-channel control is achieved.
This improved the quality and consistency of heat treatment for stator and rotor cores, ensured uniform temperature field distribution, and enhanced the stability of batch products.
Smart Images
Figure CN120905506B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of iron core heat treatment technology, and specifically to a method and system for optimizing the heat treatment process of stator and rotor iron cores based on temperature field monitoring. Background Technology
[0002] In the motor manufacturing process, the heat treatment process of the stator and rotor cores directly affects the microstructure and properties of the cores and the quality of the final product. In existing technologies, the heat treatment of stator and rotor cores typically relies on preset process parameters for overall heating, lacking precise monitoring and dynamic control of the temperature field during heat treatment. This easily leads to uneven temperature distribution, causing localized overheating or underheating of the core, resulting in differences in microstructure and properties, and affecting the stability of magnetic and mechanical properties. Furthermore, traditional heat treatment processes often employ single-channel control for parameter optimization, failing to achieve differentiated adjustments based on the core's location within the furnace, making it difficult to guarantee the consistency and reliability of batch products. Summary of the Invention
[0003] This application provides a method and system for optimizing the heat treatment process of stator and rotor cores based on temperature field monitoring, which solves the technical problems of inaccurate temperature control and poor uniformity during the heat treatment of stator and rotor cores in the prior art, resulting in unstable core quality.
[0004] The first aspect of this application provides a method for optimizing the heat treatment process of stator and rotor cores based on temperature field monitoring, the method comprising:
[0005] A predetermined number of samples are extracted from the stator and rotor cores of the target batch to obtain a sample stator and rotor core set. The sample stator and rotor core sets are then heat-treated according to predetermined heat treatment process parameters. A medium-wave thermal imager is used to monitor the temperature field through a quartz observation window to determine the locations of multiple key temperature monitoring anchor points. Based on the locations of these key temperature monitoring anchor points, the heat treatment furnace is divided into multiple temperature transmission channels. The predetermined heat treatment process parameters are then optimized using multiple channels to determine multiple channel heat treatment process parameters. Finally, the heat treatment furnace is controlled to heat-treat the stator and rotor cores of the target batch based on these multiple channel heat treatment process parameters.
[0006] A second aspect of this application provides a system for optimizing the heat treatment process of stator and rotor cores based on temperature field monitoring, the system comprising:
[0007] Sample extraction module: Extracts a preset number of samples from the stator and rotor cores of the target batch to obtain a sample stator and rotor core set; Monitoring module: Performs heat treatment on the sample stator and rotor core set according to preset heat treatment process parameters, and uses a medium-wave thermal imager to monitor the temperature field through a quartz observation window to determine the positions of multiple key temperature monitoring anchor points; Channel splitting module: Splits the temperature transmission channels of the heat treatment furnace based on the positions of the multiple key temperature monitoring anchor points to determine multiple temperature transmission channels; Parameter optimization module: Performs multi-channel optimization on the preset heat treatment process parameters based on the multiple temperature transmission channels to determine multiple channel heat treatment process parameters; Heat treatment module: Controls the heat treatment furnace to perform heat treatment on the stator and rotor cores of the target batch based on the multiple channel heat treatment process parameters.
[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:
[0009] First, a predetermined number of samples are extracted from the target batch of stator and rotor cores to obtain a sample set of stator and rotor cores. Next, the sample set of stator and rotor cores is heat-treated according to predetermined heat treatment process parameters, and a medium-wave thermal imager is used to monitor the temperature field through a quartz observation window to determine the locations of multiple key temperature monitoring anchor points. Then, based on the locations of these key temperature monitoring anchor points, the heat treatment furnace is divided into multiple temperature transmission channels. Further, based on these multiple temperature transmission channels, the predetermined heat treatment process parameters are optimized in multiple channels to determine the heat treatment process parameters for each channel. Finally, the heat treatment furnace is controlled to heat-treat the target batch of stator and rotor cores based on these multiple channel heat treatment process parameters. This solves the technical problems of inaccurate temperature control and poor uniformity during stator and rotor core heat treatment in existing technologies, leading to unstable core quality, and achieves the technical effect of improving the quality and consistency of stator and rotor core heat treatment. Attached Figure Description
[0010] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0011] Figure 1 A schematic diagram of the process optimization method for heat treatment of stator and rotor cores based on temperature field monitoring provided in the embodiments of this application;
[0012] Figure 2 A schematic diagram of the stator and rotor core heat treatment process optimization system based on temperature field monitoring provided in this application embodiment.
[0013] Figure labeling: Sample extraction module 11, monitoring module 12, channel splitting module 13, parameter optimization module 14, heat treatment module 15. Detailed Implementation
[0014] This application provides a method and system for optimizing the heat treatment process of stator and rotor cores based on temperature field monitoring, which solves the technical problems of inaccurate temperature control and poor uniformity during the heat treatment of stator and rotor cores in the prior art, resulting in unstable core quality.
[0015] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.
[0016] It should be noted that the terms "comprising" and "having" are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or modules that are not explicitly listed or that are inherent to these processes, methods, products, or devices.
[0017] Example 1, as Figure 1 As shown, this application provides a method for optimizing the heat treatment process of stator and rotor cores based on temperature field monitoring, wherein the method includes:
[0018] A predetermined number of samples are extracted from the stator and rotor cores of the target batch to obtain a sample set of stator and rotor cores.
[0019] In this embodiment, a batch information database is established for the target batch of stator and rotor cores to be heat-treated. This database includes the quantity, model specifications, production process parameters, and factory inspection records of the stator and rotor cores in that batch. Based on the batch information database, stratified random sampling or uniform interval sampling is performed from the batch of stator and rotor cores according to a preset sampling ratio or sampling quantity (e.g., 5%–10% of the total quantity or no less than 3 pieces) to ensure that the sampled samples cover different production locations and geometric specifications. Several stator and rotor cores are then numbered and registered as sample cores, establishing a sample stator and rotor core set.
[0020] The sample stator and rotor core assemblies were heat-treated according to preset heat treatment process parameters, and a medium-wave thermal imager was used to monitor the temperature field through a quartz observation window to determine the locations of multiple key temperature monitoring anchor points.
[0021] Specifically, the sample stator and rotor cores were sequentially loaded into a heat treatment furnace, and the process, including heating, holding, and cooling stages, was executed according to preset heat treatment parameters. These preset parameters included the heating rate, target temperature, holding time, and cooling method. During the heat treatment process, a mid-wave thermal imager was introduced through a quartz observation window installed on the furnace wall to monitor the end faces and key areas of the sample stator and rotor cores in real time. The mid-wave thermal imager, in conjunction with a blackbody reference source and a high-emissivity patch, performed emissivity correction and transmittance compensation on the measurement results to obtain an accurate temperature field distribution sequence. Based on the temperature field distribution sequence, a time-series analysis was performed on the temperature changes during the heating, holding, and cooling stages to identify inflection points, peak values, and stable regions of temperature changes. These locations were then used as key temperature monitoring anchor points, ultimately determining the positions of multiple key temperature monitoring anchor points.
[0022] Furthermore, the sample stator and rotor core assemblies are heat-treated according to preset heat treatment process parameters, and a medium-wave thermal imager is used to monitor the temperature field through a quartz observation window to determine the locations of multiple key temperature monitoring anchor points, including:
[0023] The sample stator and rotor cores were loaded into a heat treatment furnace and subjected to heating, holding, and cooling processes according to preset heat treatment parameters. A medium-wave thermal imager was used to monitor the temperature field through a quartz observation window. Based on the collected thermal image data, emissivity and window transmittance were corrected using a blackbody reference and a high emissivity reference patch to obtain the corrected core end face heating temperature field sequence, core end face holding temperature field sequence, and core end face cooling temperature field sequence. The positions of key temperature monitoring anchor points were identified by traversing the core end face heating temperature field sequence, core end face holding temperature field sequence, and core end face cooling temperature field sequence, obtaining sets of key temperature monitoring anchor points for heating, holding, and cooling. The positions of multiple key temperature monitoring anchor points were then integrated.
[0024] The sample stator and rotor cores are uniformly loaded into the heat treatment furnace, and the heat treatment process is carried out sequentially according to the preset heat treatment process parameters, including the heating stage, the holding stage, and the cooling stage. Optionally, in the heating stage, the temperature is increased to 500°C at 2-5°C / min, and then increased to 720-820°C at 1-3°C / min; in the holding stage, the temperature is maintained for 1.0-2.5 hours; in the cooling stage, the temperature is decreased to 200°C at 1-3°C / min and then cooled in the furnace.
[0025] Throughout the process, real-time thermal image data of the iron core end face and surrounding area is acquired using a medium-wave thermal imager through a quartz observation window placed on the furnace wall. Simultaneously, using a blackbody reference source and a high-emissivity reference patch, the acquired thermal image data undergoes emissivity correction and window transmittance compensation to eliminate measurement errors caused by material properties and the window medium, thus obtaining corrected iron core end face heating temperature field sequences, iron core end face holding temperature field sequences, and iron core end face cooling temperature field sequences. The temperature field sequences of these three stages are traversed frame by frame, and based on features such as temperature gradient changes, peak inflection points, and stable intervals, sets of key temperature monitoring anchor points for heating, holding, and cooling are extracted. Finally, these sets of key temperature monitoring anchor points are integrated, i.e., the union of the sets is used to form a unified set of key temperature monitoring anchor points.
[0026] Furthermore, this includes:
[0027] Based on the structural information of the stator and rotor cores of the target batch, a set of geometric prior anchor point locations is obtained; according to preset monitoring indicators, the set of geometric prior anchor point locations is evaluated by combining the temperature field sequence of the core end face heating, and a set of geometric prior anchor point location candidate scores is obtained; the set of geometric prior anchor point location candidate scores is filtered according to preset intervals to determine the set of key temperature monitoring anchor point locations for heating.
[0028] Furthermore, the preset monitoring indicators include at least the time to reach the temperature target, the peak value of the temperature rise slope, and the temporal stability.
[0029] Based on the structural information of the stator and rotor cores of the target batch (including the outer diameter, inner diameter, slot structure, and end-face geometric features of the core), several geometric prior locations that may exhibit temperature change characteristics are pre-defined on the core end face according to the principles of symmetry and geometric distribution, forming a set of geometric prior anchor point locations. Subsequently, pre-defined monitoring indicators are set, including at least the time to reach the temperature target, the peak value of the temperature rise slope, and temporal stability, and these are used as evaluation factors to analyze the temperature field sequence of the core end face. Based on the analysis results, each candidate location in the set of geometric prior anchor point locations is scored individually, obtaining a set of candidate scores for geometric prior anchor point locations. Then, according to a pre-defined spatial spacing threshold, the candidate score set is filtered, eliminating anchor point locations with overly dense spatial distribution or scores that do not meet the requirements. Finally, a set of representative and reasonably distributed anchor points is retained and determined as the set of key temperature monitoring anchor point locations for the temperature rise.
[0030] Based on the locations of the multiple key temperature monitoring anchor points, the temperature transmission channels of the heat treatment furnace are divided to determine multiple temperature transmission channels.
[0031] Specifically, under preset operating conditions, continuous temperature data is collected at multiple key temperature monitoring anchor points in the heat treatment furnace, forming corresponding time-series temperature sequences for each anchor point. Then, feature extraction is performed on the temperature sequences at each anchor point to obtain temperature trend features, including the rate of temperature rise, peak value variation trend, and temperature stability range. Based on these temperature trend features, the similarity relationship between each key temperature monitoring anchor point is calculated. Combined with the spatial distribution of the anchor points within the furnace cavity, temperature coupling analysis is performed to obtain temperature coupling trend features between different anchor points. Based on these temperature coupling trend features, the heat treatment furnace cavity is divided into several temperature transmission channels. Anchor points within the same channel exhibit high consistency and coupling in temperature changes, while different channels show significant temperature differences. Ultimately, multiple temperature transmission channels are obtained, each corresponding to a set of integrated temperature trend features.
[0032] Furthermore, based on the locations of the multiple key temperature monitoring anchor points, the heat treatment furnace is divided into multiple temperature transmission channels, including:
[0033] The heat treatment furnace was tested under preset operating conditions. Temperature was monitored at multiple key temperature monitoring anchor points to obtain temperature sequences at these anchor points. Temperature trend features were analyzed from these sequences to obtain temperature trend characteristics at each anchor point. Temperature coupling analysis was performed based on these trends to determine temperature coupling trend characteristics at each anchor point. Temperature transmission channels were then segmented based on these coupling trend characteristics to determine multiple temperature transmission channels, each of which includes integrated temperature trend characteristics.
[0034] During the trial operation of the heat treatment furnace according to preset operating conditions (such as set heating rate, target temperature, and holding time), real-time temperature monitoring is performed at multiple key temperature monitoring anchor points to acquire time-series temperature data covering the heating, holding, and cooling stages, forming multiple temperature sequences for key temperature monitoring anchor points. Subsequently, feature extraction and analysis are performed on the temperature sequences to obtain temperature trend features corresponding to each anchor point. These temperature trend features include temperature change rate, temperature stabilization time, temperature fluctuation amplitude, and peak characteristics. Next, based on the temperature trend features of multiple key temperature monitoring anchor points, temperature coupling analysis is performed according to the spatial proximity and temperature change similarity between anchor points to obtain multiple temperature coupling trend features reflecting the temperature transfer correlation between anchor points. Finally, based on the temperature coupling trend features, the interior of the heat treatment furnace is divided into multiple temperature transfer channels. Each temperature transfer channel contains at least one key temperature monitoring anchor point, and its integrated temperature trend features are used as the representative features of that channel, thus forming multiple temperature transfer channels reflecting the temperature field distribution law inside the furnace cavity.
[0035] Furthermore, a temperature trend feature parser is obtained, and the temperature trend feature parser is used to perform feature parsing on the temperature sequences of multiple key temperature monitoring anchor points, respectively, to obtain the temperature trend features of the multiple key temperature monitoring anchor points.
[0036] The temperature trend feature parser comprises a data preprocessing layer, a feature extraction layer, and a feature output layer. The data preprocessing layer smooths, filters, denoises, and normalizes the input temperature sequences from multiple key temperature monitoring anchor points to eliminate random interference and measurement biases during data acquisition. The feature extraction layer, based on pre-defined analytical algorithms (such as slope change detection, peak identification, time stability judgment, and frequency domain feature decomposition), analyzes each processed temperature sequence to extract multiple trend features, including heating rate, temperature reach time, temperature peak value, temperature fluctuation amplitude, and temperature stabilization duration. The feature output layer then performs structured encoding on the analyzed results to generate corresponding temperature trend feature vectors. Through this temperature trend feature parser, feature analysis is performed on the input temperature sequences from multiple key temperature monitoring anchor points, ultimately yielding the temperature trend features for each key temperature monitoring anchor point.
[0037] Furthermore, based on the temperature trend characteristics of multiple key temperature monitoring anchor points, temperature coupling analysis is performed to determine the temperature coupling trend characteristics of multiple key temperature monitoring anchor points, including:
[0038] Based on the distance between the multiple key temperature monitoring anchor points, key temperature monitoring anchor points whose distance to the multiple key temperature monitoring anchor points is within a preset monitoring distance threshold are added to their neighborhoods to obtain temperature trend feature neighborhoods for multiple key temperature monitoring anchor points. Based on the temperature trend feature neighborhoods for multiple key temperature monitoring anchor points, temperature coupling analysis is performed on the temperature trend features for the multiple key temperature monitoring anchor points to obtain temperature coupling trend features for multiple key temperature monitoring anchor points.
[0039] First, the spatial distribution coordinates of multiple key temperature monitoring anchor points within the heat treatment furnace cavity are acquired, and the interval distance between each key temperature monitoring anchor point is calculated. For any target anchor point location, if the spatial interval between other anchor points and the target anchor point is less than or equal to a preset monitoring distance threshold, then the other anchor point location is included in the neighborhood set of the target anchor point, thereby obtaining the temperature trend feature neighborhoods of multiple key temperature monitoring anchor point locations. Subsequently, for each neighborhood set, the correlation between its internal temperature trend features and the temperature trend features of the corresponding target anchor point is calculated and compared. The correlation calculation can employ feature similarity measurement methods (such as Euclidean distance, cosine similarity, or dynamic time warping methods), and the coupling degree of temperature changes is evaluated based on the calculation results. Finally, based on the correlation analysis results, the temperature coupling trend features of multiple key temperature monitoring anchor point locations are extracted and output to characterize the temperature transfer correlation between different regions.
[0040] Furthermore, based on the neighborhood of the temperature trend features at the multiple key temperature monitoring anchor points, temperature coupling analysis is performed on the temperature trend features at the multiple key temperature monitoring anchor points to obtain the temperature coupling trend features at the multiple key temperature monitoring anchor points, including:
[0041] Calculate the feature similarity sets between the neighborhood of the temperature trend features at multiple key temperature monitoring anchor points and the corresponding temperature trend features at multiple key temperature monitoring anchor points, and calculate the mean values to obtain multiple feature similarity mean sets. Normalize the multiple feature similarity mean sets to construct multiple coupling analysis vectors. Then, call a convolutional network to analyze the multiple coupling analysis vectors and the temperature trend features at multiple key temperature monitoring anchor points to obtain the temperature coupling trend features at multiple key temperature monitoring anchor points.
[0042] For any key temperature monitoring anchor point, the corresponding temperature trend features are extracted from its temperature trend feature neighborhood, and their similarity is calculated one by one with the anchor point's own temperature trend features. Similarity calculation methods can include Euclidean distance, cosine similarity, or dynamic time warping. Through this calculation process, feature similarity sets for multiple key temperature monitoring anchor point locations are obtained, and the mean of each set is calculated to obtain the corresponding feature similarity mean set. Next, the feature similarity mean sets are normalized to eliminate numerical scale differences between different anchor points, generating standardized similarity vectors. Further, the normalized results are constructed into multiple coupling analysis vectors and input into a pre-defined convolutional network. The convolutional network, through convolution operations and feature fusion, comprehensively analyzes the coupling analysis vectors and their corresponding temperature trend features, thereby identifying the temperature change coupling relationship between the anchor point and its neighborhood. Finally, the temperature coupling trend features of multiple key temperature monitoring anchor point locations are output to characterize the transmission and coupling patterns between temperature fields in different regions.
[0043] Based on the multiple temperature transfer channels, the preset heat treatment process parameters are optimized in multiple channels to determine the heat treatment process parameters for multiple channels.
[0044] Based on the temperature transfer channel segmentation results, the temperature field within the heat treatment furnace cavity is divided into multiple independent temperature transfer channels, and the temperature integration trend characteristics of each channel are extracted. Using the temperature integration trend characteristics of each channel as input parameters, the channel optimizer is invoked to analyze the preset heat treatment process parameters, initially generating multiple corresponding channel heat treatment process parameters, including heating rate, target temperature, holding time, cooling rate, and atmosphere conditioning method. Further, nearest neighbor interference analysis is performed on the initial channel heat treatment process parameters, i.e., cross-coupling calculations are performed on channel parameters that are spatially adjacent or whose temperature transfer affects each other, to identify parameter combinations that may cause local overheating or underheating. Based on the analysis results, parameters with interference risks are corrected and optimized to form the final heat treatment process parameters for each channel. Ultimately, the determined multiple channel heat treatment process parameters can provide differentiated control for the temperature transfer characteristics of different regions.
[0045] Furthermore, based on the multiple temperature transfer channels, the preset heat treatment process parameters are optimized through multiple channels to determine the heat treatment process parameters for multiple channels, including:
[0046] Based on the temperature integration trend characteristics corresponding to the multiple temperature transfer channels, the channel optimizer is invoked for analysis to determine the heat treatment process parameters of multiple initial channels; nearest neighbor interference analysis is performed on the heat treatment process parameters of the multiple initial channels, and the parameters are optimized according to the analysis results to obtain the heat treatment process parameters of the multiple channels.
[0047] Based on the aforementioned temperature transfer channel segmentation results, the temperature integration trend features corresponding to each channel are extracted. These features include temperature change rate, stable range, fluctuation amplitude, and peak offset. Subsequently, the temperature integration trend features of each channel are input into a channel optimizer for analysis. The optimizer generates multiple initial channel heat treatment process parameters by comparing the fit between preset process parameters and channel features, including heating rate, target heating temperature, holding time, and cooling curve. Next, a nearest neighbor interference analysis is performed on the generated initial channel heat treatment process parameters. This involves evaluating the coupling effect and interference degree between process parameters for channels that are spatially adjacent or whose temperature transfer influence ranges overlap. Based on the results of the nearest neighbor interference analysis, parameters with conflicts or potential imbalances are corrected and optimized to avoid local overheating or underheating. Finally, a set of optimized channel heat treatment process parameters is obtained, enabling differentiated control of different temperature transfer channels, thereby improving the overall heat treatment uniformity and batch consistency of the stator and rotor cores.
[0048] The heat treatment furnace is controlled to perform heat treatment on the target batch of stator and rotor cores based on the heat treatment process parameters of the multiple channels.
[0049] After obtaining multiple optimized heat treatment process parameters for each channel, these parameters are allocated to corresponding temperature transfer channels within the heat treatment furnace, and differentiated control is achieved through a multi-zone temperature control device within the furnace. For each temperature transfer channel, the control system precisely adjusts the power output of the heating elements, the flow rate of the atmosphere conditioning components, and the start-up and shutdown sequence of the cooling fan or coolant based on the allocated channel process parameters. This ensures that the stator and rotor cores within that channel meet the corresponding process requirements in terms of heating rate, target temperature, holding time, and cooling rate.
[0050] Throughout the heat treatment process of the target batch, the system collects temperature feedback information at each key anchor point in real time and compares it with the set channel process parameters. When a deviation is detected that exceeds the allowable range, the heating or cooling intensity of that channel is immediately adjusted through a closed-loop control algorithm to achieve dynamic compensation control. Ultimately, under the synergistic effect of multiple channel process parameters, the overall heat treatment of the stator and rotor cores of the target batch is completed, thereby ensuring a uniform temperature field distribution in different locations of the core and significantly improving the heat treatment quality and consistency of the batch products.
[0051] In summary, the embodiments of this application have at least the following technical effects:
[0052] First, a predetermined number of samples are extracted from the target batch of stator and rotor cores to obtain a sample set of stator and rotor cores. Next, the sample set of stator and rotor cores is heat-treated according to predetermined heat treatment process parameters, and a medium-wave thermal imager is used to monitor the temperature field through a quartz observation window to determine the locations of multiple key temperature monitoring anchor points. Then, based on the locations of these key temperature monitoring anchor points, the heat treatment furnace is divided into multiple temperature transmission channels. Further, based on these multiple temperature transmission channels, the predetermined heat treatment process parameters are optimized in multiple channels to determine the heat treatment process parameters for each channel. Finally, the heat treatment furnace is controlled to heat-treat the target batch of stator and rotor cores based on these multiple channel heat treatment process parameters. This solves the technical problems of inaccurate temperature control and poor uniformity during stator and rotor core heat treatment in existing technologies, leading to unstable core quality, and achieves the technical effect of improving the quality and consistency of stator and rotor core heat treatment.
[0053] Example 2 is based on the same inventive concept as the temperature field monitoring-based stator and rotor core heat treatment process optimization method in the aforementioned examples, such as... Figure 2 As shown, this application provides a system for optimizing the heat treatment process of stator and rotor cores based on temperature field monitoring, wherein the system includes:
[0054] Sample extraction module 11: Extracts a preset number of samples from the stator and rotor cores of the target batch to obtain a sample stator and rotor core set; Monitoring module 12: Performs heat treatment on the sample stator and rotor core set according to preset heat treatment process parameters, and calls a medium-wave thermal imager to monitor the temperature field through a quartz observation window to determine the positions of multiple key temperature monitoring anchor points; Channel splitting module 13: Splits the temperature transmission channels of the heat treatment furnace based on the positions of the multiple key temperature monitoring anchor points to determine multiple temperature transmission channels; Parameter optimization module 14: Performs multi-channel optimization on the preset heat treatment process parameters based on the multiple temperature transmission channels to determine multiple channel heat treatment process parameters; Heat treatment module 15: Controls the heat treatment furnace to perform heat treatment on the stator and rotor cores of the target batch based on the multiple channel heat treatment process parameters.
[0055] Furthermore, the monitoring module 12 is used to perform the following methods:
[0056] The sample stator and rotor cores were loaded into a heat treatment furnace and subjected to heating, holding, and cooling processes according to preset heat treatment parameters. A medium-wave thermal imager was used to monitor the temperature field through a quartz observation window. Based on the collected thermal image data, emissivity and window transmittance were corrected using a blackbody reference and a high emissivity reference patch to obtain the corrected core end face heating temperature field sequence, core end face holding temperature field sequence, and core end face cooling temperature field sequence. The positions of key temperature monitoring anchor points were identified by traversing the core end face heating temperature field sequence, core end face holding temperature field sequence, and core end face cooling temperature field sequence, obtaining sets of key temperature monitoring anchor points for heating, holding, and cooling. The positions of multiple key temperature monitoring anchor points were then integrated.
[0057] Furthermore, the monitoring module 12 is used to perform the following methods:
[0058] Based on the structural information of the stator and rotor cores of the target batch, a set of geometric prior anchor point locations is obtained; according to preset monitoring indicators, the set of geometric prior anchor point locations is evaluated by combining the temperature field sequence of the core end face heating, and a set of geometric prior anchor point location candidate scores is obtained; the set of geometric prior anchor point location candidate scores is filtered according to preset intervals to determine the set of key temperature monitoring anchor point locations for heating.
[0059] Furthermore, the monitoring module 12 is used to perform the following methods:
[0060] The preset monitoring indicators include at least the time to reach the temperature target, the peak value of the temperature rise slope, and the time series stability.
[0061] Furthermore, the channel splitting module 13 is used to perform the following method:
[0062] The heat treatment furnace was tested under preset operating conditions. Temperature was monitored at multiple key temperature monitoring anchor points to obtain temperature sequences at these anchor points. Temperature trend features were analyzed from these sequences to obtain temperature trend characteristics at each anchor point. Temperature coupling analysis was performed based on these trends to determine temperature coupling trend characteristics at each anchor point. Temperature transmission channels were then segmented based on these coupling trend characteristics to determine multiple temperature transmission channels, each of which includes integrated temperature trend characteristics.
[0063] Furthermore, the channel splitting module 13 is used to perform the following method:
[0064] A temperature trend feature parser is obtained, and the temperature trend feature parser is used to perform feature parsing on the temperature sequences of multiple key temperature monitoring anchor points, respectively, to obtain the temperature trend features of the multiple key temperature monitoring anchor points.
[0065] Furthermore, the channel splitting module 13 is used to perform the following method:
[0066] Based on the distance between the multiple key temperature monitoring anchor points, key temperature monitoring anchor points whose distance to the multiple key temperature monitoring anchor points is within a preset monitoring distance threshold are added to their neighborhoods to obtain temperature trend feature neighborhoods for multiple key temperature monitoring anchor points. Based on the temperature trend feature neighborhoods for multiple key temperature monitoring anchor points, temperature coupling analysis is performed on the temperature trend features for the multiple key temperature monitoring anchor points to obtain temperature coupling trend features for multiple key temperature monitoring anchor points.
[0067] Furthermore, the channel splitting module 13 is used to perform the following method:
[0068] Calculate the feature similarity sets between the neighborhood of the temperature trend features at multiple key temperature monitoring anchor points and the corresponding temperature trend features at multiple key temperature monitoring anchor points, and calculate the mean values to obtain multiple feature similarity mean sets. Normalize the multiple feature similarity mean sets to construct multiple coupling analysis vectors. Then, call a convolutional network to analyze the multiple coupling analysis vectors and the temperature trend features at multiple key temperature monitoring anchor points to obtain the temperature coupling trend features at multiple key temperature monitoring anchor points.
[0069] Furthermore, the parameter optimization module 14 is used to perform the following method:
[0070] Based on the temperature integration trend characteristics corresponding to the multiple temperature transfer channels, the channel optimizer is invoked for analysis to determine the heat treatment process parameters of multiple initial channels; nearest neighbor interference analysis is performed on the heat treatment process parameters of the multiple initial channels, and the parameters are optimized according to the analysis results to obtain the heat treatment process parameters of the multiple channels.
[0071] It should be noted that the order of the embodiments described above is for descriptive purposes only and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.
[0072] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.
[0073] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and modifications fall within the scope of this application and its equivalents, this application intends to include such modifications and modifications.
Claims
1. A method for optimizing the heat treatment process of stator and rotor cores based on temperature field monitoring, characterized in that, The method includes: A predetermined number of samples are extracted from the stator and rotor cores of the target batch to obtain a sample set of stator and rotor cores; The sample stator and rotor core assemblies were heat-treated according to preset heat treatment process parameters, and a medium-wave thermal imager was used to monitor the temperature field through a quartz observation window to determine the positions of multiple key temperature monitoring anchor points. Based on the locations of the multiple key temperature monitoring anchor points, the temperature transmission channels of the heat treatment furnace are divided to determine multiple temperature transmission channels. Based on the multiple temperature transfer channels, the preset heat treatment process parameters are optimized in multiple channels to determine the heat treatment process parameters for multiple channels. The heat treatment furnace is controlled to perform heat treatment on the target batch of stator and rotor cores based on the heat treatment process parameters of the multiple channels. Based on the locations of the multiple key temperature monitoring anchor points, the heat treatment furnace is divided into multiple temperature transmission channels, including: The heat treatment furnace was tested under preset operating conditions, and the temperature of the multiple key temperature monitoring anchor points was monitored to obtain the temperature sequence of the multiple key temperature monitoring anchor points. Temperature trend features of the temperature sequences at the multiple key temperature monitoring anchor points are analyzed to obtain temperature trend features at the multiple key temperature monitoring anchor points. Temperature coupling analysis was conducted based on the temperature trend characteristics of multiple key temperature monitoring anchor points to determine the temperature coupling trend characteristics of multiple key temperature monitoring anchor points. Temperature transmission channels are split based on the temperature coupling trend characteristics of the multiple key temperature monitoring anchor points, and the multiple temperature transmission channels are determined, wherein each temperature transmission channel includes temperature integration trend characteristics.
2. The method for optimizing the heat treatment process of stator and rotor cores based on temperature field monitoring as described in claim 1, characterized in that, The sample stator and rotor core assemblies were heat-treated according to preset heat treatment process parameters, and a medium-wave thermal imager was used to monitor the temperature field through a quartz observation window to determine the locations of several key temperature monitoring anchor points, including: The sample stator and rotor cores are assembled and placed into a heat treatment furnace, and then heated, held and cooled according to the preset heat treatment process parameters. A medium-wave thermal imager was used to monitor the temperature field through a quartz observation window. Based on the collected thermal image data, emissivity and window transmittance were corrected by combining a blackbody reference and a high emissivity reference. The corrected core end face heating temperature field sequence, core end face insulation temperature field sequence, and core end face cooling temperature field sequence were obtained. The key temperature monitoring anchor point positions are identified by traversing the core end face heating temperature field sequence, core end face insulation temperature field sequence and core end face cooling temperature field sequence, so as to obtain the set of key temperature monitoring anchor point positions for heating, insulation and cooling. By integrating the sets of key temperature monitoring anchor points for heating, insulation, and cooling, multiple key temperature monitoring anchor point locations are obtained.
3. The method for optimizing the heat treatment process of stator and rotor cores based on temperature field monitoring as described in claim 2, characterized in that, include: Based on the structural information of the stator and rotor cores of the target batch, a set of geometric prior anchor point positions is obtained; According to the preset monitoring indicators, the set of geometric prior anchor points is evaluated by combining the temperature field sequence of the iron core end face heating, and a set of candidate scores for geometric prior anchor points is obtained. The set of candidate scores for geometric prior anchor point positions is filtered according to a preset interval to determine the set of key temperature monitoring anchor point positions for temperature rise.
4. The method for optimizing the heat treatment process of stator and rotor cores based on temperature field monitoring as described in claim 3, characterized in that, The preset monitoring indicators include at least the time to reach the temperature target, the peak value of the temperature rise slope, and the time series stability.
5. The method for optimizing the heat treatment process of stator and rotor cores based on temperature field monitoring as described in claim 1, characterized in that, A temperature trend feature parser is obtained, and the temperature trend feature parser is used to perform feature parsing on the temperature sequences of multiple key temperature monitoring anchor points, respectively, to obtain the temperature trend features of the multiple key temperature monitoring anchor points.
6. The method for optimizing the heat treatment process of stator and rotor cores based on temperature field monitoring as described in claim 1, characterized in that, Temperature coupling analysis was conducted based on the temperature trend characteristics of multiple key temperature monitoring anchor points to determine the temperature coupling trend characteristics of these anchor points, including: Based on the distance between the multiple key temperature monitoring anchor points, the key temperature monitoring anchor points whose distance to the multiple key temperature monitoring anchor points is within a preset monitoring distance threshold are added to their neighborhood to obtain the temperature trend feature neighborhood of the multiple key temperature monitoring anchor points. Based on the neighborhood of the temperature trend features of the multiple key temperature monitoring anchor points, temperature coupling analysis is performed on the temperature trend features of the multiple key temperature monitoring anchor points to obtain the temperature coupling trend features of the multiple key temperature monitoring anchor points.
7. The method for optimizing the heat treatment process of stator and rotor cores based on temperature field monitoring as described in claim 6, characterized in that, Based on the neighborhood of the temperature trend features at the locations of the multiple key temperature monitoring anchor points, temperature coupling analysis is performed on the temperature trend features at the locations of the multiple key temperature monitoring anchor points to obtain the temperature coupling trend features at the locations of the multiple key temperature monitoring anchor points, including: Calculate the feature similarity set between the neighborhood of the temperature trend feature of multiple key temperature monitoring anchor points and the corresponding temperature trend feature of multiple key temperature monitoring anchor points, and calculate the mean to obtain multiple feature similarity mean sets. The mean values of the multiple feature similarities are normalized to construct multiple coupling analysis vectors. A convolutional network is then called to analyze the multiple coupling analysis vectors and the temperature trend features of multiple key temperature monitoring anchor points to obtain the temperature coupling trend features of multiple key temperature monitoring anchor points.
8. The method for optimizing the heat treatment process of stator and rotor cores based on temperature field monitoring as described in claim 1, characterized in that, Based on the multiple temperature transfer channels, the preset heat treatment process parameters are optimized through multiple channels to determine the heat treatment process parameters for multiple channels, including: Based on the temperature integration trend characteristics corresponding to the multiple temperature transfer channels, the channel optimizer is invoked for analysis to determine the heat treatment process parameters of multiple initial channels. Nearest neighbor interference analysis was performed on the heat treatment process parameters of the multiple initial channels, and the parameters were optimized based on the analysis results to obtain the heat treatment process parameters of the multiple channels.
9. A system for optimizing the heat treatment process of stator and rotor cores based on temperature field monitoring, characterized in that, The system is used to implement the method for optimizing the heat treatment process of stator and rotor cores based on temperature field monitoring as described in any one of claims 1-8, the system comprising: Sample extraction module: Extracts a preset number of samples from the stator and rotor cores of the target batch to obtain a sample set of stator and rotor cores; Monitoring module: The sample stator and rotor core assembly is heat-treated according to preset heat treatment process parameters, and a medium-wave thermal imager is used to monitor the temperature field through a quartz observation window to determine the location of multiple key temperature monitoring anchor points; Channel splitting module: Based on the locations of the multiple key temperature monitoring anchor points, the heat treatment furnace is split into multiple temperature transmission channels; Parameter optimization module: Based on the multiple temperature transfer channels, the preset heat treatment process parameters are optimized in multiple channels to determine the heat treatment process parameters for multiple channels; Heat treatment module: Controls the heat treatment furnace to perform heat treatment on the target batch of stator and rotor cores based on the heat treatment process parameters of the multiple channels.
Citation Information
Patent Citations
Irregular metal forge piece heat treatment method and system
CN120758729A