A method and system for residual stress reduction control of titanium alloy swage

Abstract

The present application relates to the technical field of alloy production, and discloses a titanium alloy die forging residual stress reduction control method and system, which comprises the following steps: based on initial state data, performing multi-physical field coupling vibration regulation and control on the titanium alloy die forging to obtain multi-dimensional vibration control parameters; based on the multi-dimensional vibration control parameters, applying multi-directional vibration to the titanium alloy die forging to obtain dynamic response data; performing multi-modal data fusion on the dynamic response data to obtain residual stress reduction evaluation indexes; based on the residual stress reduction evaluation indexes, performing multi-objective decision on the multi-dimensional vibration control parameters to obtain optimized vibration parameters; based on the optimized vibration parameters, performing robustness analysis on the vibration control instruction sequence of the titanium alloy die forging to obtain final control instructions; and based on the final control instructions, performing multi-dimensional verification on the residual stress reduction effect to obtain a final residual stress reduction report; the present application can improve the residual stress reduction efficiency of the titanium alloy die forging.

Description

Technical Field

[0001] This invention relates to the field of alloy production technology, and in particular to a method and system for controlling residual stress reduction in titanium alloy forgings. Background Technology

[0002] Existing residual stress reduction technologies for titanium alloy forgings mostly rely on a single physical field control method, which is difficult to fully adapt to the complex geometric configuration and material property differences of forgings. Such technologies often fail to incorporate historical process data for parameter optimization, resulting in insufficient targeting of vibration control parameters. This makes it impossible to effectively stimulate the internal stress release mechanism of the forgings, ultimately leading to low residual stress reduction efficiency and failing to meet the stringent requirements of high-precision manufacturing for residual stress control.

[0003] Traditional techniques lack multimodal fusion analysis of dynamic response data during residual stress reduction, making it impossible to comprehensively and accurately assess the stress reduction effect. Furthermore, subsequent parameter adjustments rely heavily on empirical judgments and fail to optimize parameters through multi-objective decision-making and robustness analysis. This not only easily leads to instruction execution deviations but also results in poor stability of the stress reduction effect, making it difficult to ensure the performance consistency of titanium alloy forgings in mass production. Summary of the Invention

[0004] This invention provides a method and system for controlling residual stress reduction in titanium alloy forgings to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides a method for controlling residual stress reduction in titanium alloy forgings, comprising:

[0006] S1. Based on the initial state data of the titanium alloy forging, multi-physics field coupled vibration regulation is performed on the titanium alloy forging to obtain the multi-dimensional vibration control parameters of the titanium alloy forging.

[0007] S2. Based on the multi-dimensional vibration control parameters, apply multi-directional vibration to the titanium alloy forging to obtain the dynamic response data of the titanium alloy forging;

[0008] S3. Perform multimodal data fusion on the dynamic response data to obtain the residual stress reduction evaluation index of the titanium alloy forging;

[0009] S4. Based on the residual stress reduction evaluation index, perform multi-objective decision-making on the multi-dimensional vibration control parameters to obtain the optimized vibration parameters of the titanium alloy forging.

[0010] S5. Based on the optimized vibration parameters, perform robustness analysis on the vibration control command sequence of the titanium alloy forging to obtain the final control command of the titanium alloy forging.

[0011] S6. Based on the final control command, the residual stress reduction effect of the titanium alloy forging is verified in multiple dimensions to obtain the final residual stress reduction report of the titanium alloy forging.

[0012] In a preferred embodiment, the multi-physics field coupled vibration modulation of the titanium alloy forging is performed based on the initial state data of the titanium alloy forging to obtain multi-dimensional vibration control parameters of the titanium alloy forging, including:

[0013] Feature extraction is performed on the historical process data in the initial state data to obtain the process influence factor of the titanium alloy forging;

[0014] By coupling the geometric configuration data, material property data, and process influence factors in the initial state data, the comprehensive state data of the titanium alloy forging is obtained.

[0015] The initial control parameters of the titanium alloy forging are obtained by performing multiphysics field constraint optimization on the comprehensive state data.

[0016] The initial control parameters are checked for coordination to obtain the multi-dimensional vibration control parameters of the titanium alloy forging.

[0017] In a preferred embodiment, the step of applying multi-directional vibration to the titanium alloy forging based on the multi-dimensional vibration control parameters to obtain the dynamic response data of the titanium alloy forging includes:

[0018] Modal decoupling is performed on the multi-dimensional vibration control parameters to obtain the independent vibration command sequence of the titanium alloy forging;

[0019] Based on the response acquisition channel of the simulated virtual space, multi-directional vibration is applied to the titanium alloy forging to obtain the primary response flow of the titanium alloy forging;

[0020] Time-frequency domain analysis was performed on the primary response flow to obtain various dynamic indicators of the titanium alloy forging.

[0021] The dynamic response data of the titanium alloy forging is obtained by aligning the various dynamic indicators with timestamps.

[0022] In a preferred embodiment, the response acquisition channel based on simulated virtual space applies multi-directional vibration to the titanium alloy forging to obtain the primary response flow of the titanium alloy forging, including:

[0023] Based on the geometric configuration data in the initial state data, virtual measuring points are defined on the titanium alloy forging.

[0024] Based on the virtual measuring points, construct a response data acquisition network connecting the virtual measuring points;

[0025] Based on the response data acquisition network, the independent vibration command sequence is applied to the titanium alloy forging to obtain the original response signal of the titanium alloy forging;

[0026] The original response signal is subjected to integrity verification to obtain the primary response flow of the titanium alloy forging.

[0027] In a preferred embodiment, the step of performing multimodal data fusion on the dynamic response data to obtain the residual stress reduction evaluation index of the titanium alloy forging includes:

[0028] The dynamic response data is subjected to signal integrity verification to obtain the verified dynamic response data of the titanium alloy forging.

[0029] Empirical mode decomposition is performed on the verified dynamic response data to obtain the intrinsic mode components of the titanium alloy forging.

[0030] Based on the sample entropy of the intrinsic mode components, construct the weighted fusion matrix of the intrinsic mode components;

[0031] Based on the weighted fusion matrix, the residual stress reduction assessment index is calculated, wherein the calculation formula for the residual stress reduction assessment index is:

[0032] ;

[0033] in, This represents the residual stress reduction assessment index. This represents the total number of the intrinsic modal components. Indicates the first The weights of the intrinsic mode components. This represents the total number of data points for each of the intrinsic mode components. Indicates the first The intrinsic mode components are at time... Quantity, Indicates the first The average value of each intrinsic mode component.

[0034] In a preferred embodiment, constructing the weighted fusion matrix of the intrinsic mode components based on the sample entropy of the intrinsic mode components includes:

[0035] Based on a preset weight range, the sample entropy is reconstructed to obtain the initial weights of the titanium alloy forging.

[0036] The initial weights are normalized to obtain the final weights of the titanium alloy forgings.

[0037] The final weights are assigned to the intrinsic mode components according to the corresponding relationship to form a weighted fusion matrix of the intrinsic mode components.

[0038] In a preferred embodiment, the step of performing multi-objective decision-making on the multi-dimensional vibration control parameters based on the residual stress reduction evaluation index to obtain the optimized vibration parameters of the titanium alloy forging includes:

[0039] The residual stress reduction evaluation index is standardized in multiple dimensions to obtain the standardized evaluation index of the titanium alloy forging.

[0040] Based on the standardized evaluation index, the multi-dimensional vibration control parameters are prioritized to obtain the degree of influence of the multi-dimensional vibration control parameters on the reduction of residual stress in the titanium alloy forging.

[0041] Based on the degree of influence, a multi-objective trade-off analysis is performed on the multi-dimensional vibration control parameters to obtain the preliminary optimized parameters of the titanium alloy forging.

[0042] The initial optimized parameters were verified for consistency to obtain the optimized vibration parameters of the titanium alloy forging.

[0043] In a preferred embodiment, prioritizing the multi-dimensional vibration control parameters based on the standardized evaluation indicators to obtain the degree of influence of the multi-dimensional vibration control parameters on the reduction of residual stress in the titanium alloy forging includes:

[0044] The key features in the multi-dimensional vibration control parameters are analyzed to obtain the parameter feature set of the multi-dimensional vibration control parameters;

[0045] Correlation analysis is performed on the parameter feature set to obtain similarity characteristic data of the multi-dimensional vibration control parameters;

[0046] Based on the correspondence between the similarity characteristic data and the standardized evaluation indicators, the multi-dimensional vibration control parameters are comprehensively evaluated to obtain the degree of influence of the multi-dimensional vibration control parameters on the reduction of residual stress in the titanium alloy forging.

[0047] In a preferred embodiment, the robustness analysis of the vibration control command sequence of the titanium alloy forging based on the optimized vibration parameters to obtain the final control command of the titanium alloy forging includes:

[0048] Uncertainty quantification is performed on the optimized vibration parameters to obtain the parameter fluctuation range of the titanium alloy forging;

[0049] Based on the parameter fluctuation range, multi-scenario disturbance simulation is performed on the vibration control command sequence to obtain the command execution deviation dataset of the titanium alloy forging.

[0050] The stability of the instruction execution deviation dataset is evaluated to obtain its stability level.

[0051] Based on the stability level, the vibration control command sequence is adjusted to a fault-tolerant structure to obtain the final control command for the titanium alloy forging.

[0052] To address the above problems, the present invention also provides a residual stress reduction control system for titanium alloy forgings, the system comprising:

[0053] The vibration parameter control module is used to perform multi-physics field coupled vibration control on the titanium alloy forging based on the initial state data of the titanium alloy forging, so as to obtain the multi-dimensional vibration control parameters of the titanium alloy forging.

[0054] A dynamic response vibration module is used to apply multi-directional vibration to the titanium alloy forging based on the multi-dimensional vibration control parameters to obtain the dynamic response data of the titanium alloy forging.

[0055] The residual stress assessment module is used to perform multimodal data fusion on the dynamic response data to obtain the residual stress reduction assessment index of the titanium alloy forging.

[0056] The vibration parameter optimization module is used to make multi-objective decisions on the multi-dimensional vibration control parameters based on the residual stress reduction evaluation index, so as to obtain the optimized vibration parameters of the titanium alloy forging.

[0057] An optimized control command module is used to perform robustness analysis on the vibration control command sequence of the titanium alloy forging based on the optimized vibration parameters, and to obtain the final control command of the titanium alloy forging.

[0058] The residual stress verification module is used to perform multi-dimensional verification of the residual stress reduction effect of the titanium alloy forging based on the final control command, and obtain the final residual stress reduction report of the titanium alloy forging.

[0059] Compared with the prior art, the present invention has the following beneficial effects:

[0060] 1. This invention obtains multi-dimensional vibration control parameters through multi-physics field coupling vibration regulation, and generates residual stress reduction evaluation index by combining multi-modal data fusion. It can accurately capture the dynamic response of the forging part during vibration, making the evaluation of residual stress reduction effect more comprehensive, providing a reliable basis for subsequent parameter optimization, and thus improving the final reduction effect.

[0061] 2. This invention optimizes vibration parameters through multi-objective decision-making and then obtains the final control command through robustness analysis, reducing the repetitiveness of parameter tuning and shortening the control process cycle; moreover, robustness analysis can cope with parameter fluctuations, ensuring stable execution of control commands under different scenarios, guaranteeing the continuity and reliability of the residual stress reduction process, and further improving the overall control efficiency. Attached Figure Description

[0062] Figure 1 This is a flowchart illustrating a method for controlling residual stress reduction in titanium alloy forgings according to an embodiment of the present invention.

[0063] Figure 2 This is a functional block diagram of a residual stress reduction control system for titanium alloy forgings provided in an embodiment of the present invention;

[0064] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0065] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0066] This application provides a method for controlling residual stress reduction in titanium alloy forgings. The execution subject of this method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the method for controlling residual stress reduction in titanium alloy forgings can be executed by software or hardware installed on a terminal device or a server device. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0067] Reference Figure 1The diagram shown is a flowchart illustrating a method for reducing and controlling residual stress in titanium alloy forgings according to an embodiment of the present invention. In this embodiment, the method for reducing and controlling residual stress in titanium alloy forgings includes:

[0068] S1. Based on the initial state data of the titanium alloy forging, multi-physics field coupled vibration regulation is performed on the titanium alloy forging to obtain the multi-dimensional vibration control parameters of the titanium alloy forging.

[0069] In this embodiment of the invention, the multi-physics field coupled vibration regulation of the titanium alloy forging based on its initial state data is used to obtain multi-dimensional vibration control parameters for the titanium alloy forging, including:

[0070] Feature extraction is performed on the historical process data in the initial state data to obtain the process influence factor of the titanium alloy forging;

[0071] By coupling the geometric configuration data, material property data, and process influence factors in the initial state data, the comprehensive state data of the titanium alloy forging is obtained.

[0072] The initial control parameters of the titanium alloy forging are obtained by performing multiphysics field constraint optimization on the comprehensive state data.

[0073] The initial control parameters are checked for coordination to obtain the multi-dimensional vibration control parameters of the titanium alloy forging.

[0074] Specifically, when extracting features from historical process data in the initial state data to obtain process influencing factors, it is necessary to first collect complete historical process data from the past production of titanium alloy forgings. This data includes, but is not limited to, key process parameters such as forging temperature, forging pressure, holding time, and cooling rate used in the previous production of this type of forging, as well as related data such as residual stress detection results and forming quality feedback of the forgings under the corresponding process. Subsequently, the collected historical process data is classified and sorted according to the process steps. For example, forging temperature-related data is grouped into one category, and forging pressure-related data is grouped into another category, ensuring that each category of data corresponds to a clear process operation. Next, the correlation between various types of historical process data and the residual stress reduction effect of forgings is analyzed, and process data items that have a significant impact on residual stress reduction are screened out. For example, by comparing the residual stress values ​​of forgings at different forging temperatures, it is determined that forging temperature is a key influencing data item. These screened key process data items and their corresponding influence patterns are integrated to form the process influencing factors of titanium alloy forgings.

[0075] Furthermore, when coupling the geometric configuration data, material property data, and process influence factors in the initial state data to obtain comprehensive state data, the specific content of each data item is first clarified. Geometric configuration data includes detailed information such as the three-dimensional dimensions, shape characteristics, and structural complexity of the titanium alloy forging; material property data includes parameters such as the composition, mechanical properties, and thermophysical properties of the titanium alloy; and process influence factors are the key process data items and their influencing patterns identified in previous steps. Then, a data association mapping relationship is established, matching different dimensions and shape characteristics in the geometric configuration data with the corresponding mechanical and thermophysical properties in the material property data. For example, the wall thickness data of a certain part of the forging needs to be matched with the thermal conductivity and elastic modulus data of the titanium alloy material in that part. Simultaneously, the key process parameters in the process influence factors are associated with the geometric configuration data and material property data; for example, the forging temperature process influence factor needs to be associated with the overall geometric dimensions of the forging and the coefficient of thermal expansion of the material. Finally, following a unified data format and logical framework, the associated geometric configuration data, material property data, and process influence factors are integrated to form comprehensive state data containing all information about the forging.

[0076] Furthermore, when performing multi-physics field constraint optimization on the comprehensive state data to obtain initial control parameters, the specific types of multi-physics fields are first identified, including mechanical vibration fields, temperature fields, stress fields, and other physical fields related to the reduction of residual stress in titanium alloy forgings. Next, constraints are set for each physical field. For the mechanical vibration field, constraints include the vibration frequency range and upper limit of vibration amplitude; for the temperature field, constraints include the temperature control range and temperature change rate limit; and for the stress field, constraints include the initial stress threshold. Then, based on the geometric configuration, material properties, and process influence factors in the comprehensive state data, the interaction relationships between the various physical fields are analyzed. For example, changes in the vibration parameters of the mechanical vibration field affect the heat distribution of the temperature field, and temperature changes in the temperature field alter the mechanical properties of the material, thus affecting the stress state of the stress field. Based on these interaction relationships, the control parameters of each physical field are adjusted. Under the premise of satisfying all constraints, the combination of parameters of each physical field can maximize the release of residual stress in the forging. The adjusted control parameters of each physical field are then integrated to form the initial control parameters for the titanium alloy forging.

[0077] Furthermore, when performing a coordination verification on the initial control parameters to obtain multi-dimensional vibration control parameters, the core content of the coordination verification should first be clarified, namely, checking whether there are any conflicts between the various physical field control parameters in the initial control parameters, and whether each parameter matches the comprehensive state data of the titanium alloy forging. Specifically, the mechanical vibration parameters, temperature control parameters, etc., in the initial control parameters should be broken down one by one, and the correlation between different parameters should be analyzed. For example, it should be checked whether the vibration frequency matches the temperature control parameters. If the vibration frequency is too high and the temperature control is inappropriate, it may lead to local overheating or increased stress concentration in the forging. Then, combined with the geometric configuration data and material property data in the comprehensive state data, it should be verified whether the initial control parameters are suitable for the forging. For example, for thin-walled forgings, it is necessary to check whether the amplitude in the initial control parameters is suitable for the forging. Excessive amplitude can cause deformation in thin-walled sections. For high-strength titanium alloy forgings, it is necessary to confirm whether the temperature control range in the initial control parameters can effectively soften the material and promote stress release. For parameter conflicts or mismatches found during the verification process, the initial control parameters are adjusted and optimized based on the comprehensive state data of the forgings and the residual stress reduction target. For example, when there is a conflict between the vibration frequency and temperature parameters, the vibration frequency is reduced while the control temperature is appropriately increased to ensure that the two work together to promote stress release. After multiple verifications and adjustments, until there are no conflicts between the parameters in the initial control parameters and they are fully adapted to the comprehensive state of the forgings, the final determined physical field control parameters are classified and organized according to the dimensions of vibration control to form multi-dimensional vibration control parameters covering mechanical vibration, temperature assistance, and other aspects.

[0078] In summary, by extracting historical process data features from the initial state data and identifying process influencing factors, we can accurately pinpoint the effects of past processes on the residual stress of titanium alloy forgings, providing data support for subsequent control and reducing control deviations caused by missing process information. Coupled geometric configuration data, material property data, and process influencing factors to form comprehensive state data, we can fully integrate the characteristics of the forgings themselves and process factors, avoiding the limitations of a single data dimension and providing a more complete data foundation for subsequent optimization.

[0079] In summary, multi-physics field constraint optimization of comprehensive state data can combine the interaction of different physical fields to ensure that the initial control parameters meet the residual stress reduction requirements under the synergistic effect of multiple fields, thereby improving the scientific nature of the parameters. Coordination verification of the initial control parameters can ensure that there are no conflicts between the parameters and that they are highly adaptable, avoiding vibration control failure or poor effect due to parameter contradictions. This ensures that multi-dimensional vibration control parameters can stably act on the forgings, effectively improving the efficiency and reliability of residual stress reduction.

[0080] S2. Based on the multi-dimensional vibration control parameters, apply multi-directional vibration to the titanium alloy forging to obtain the dynamic response data of the titanium alloy forging;

[0081] In this embodiment of the invention, the step of applying multi-directional vibration to the titanium alloy forging based on the multi-dimensional vibration control parameters to obtain the dynamic response data of the titanium alloy forging includes:

[0082] Modal decoupling is performed on the multi-dimensional vibration control parameters to obtain the independent vibration command sequence of the titanium alloy forging;

[0083] Based on the response acquisition channel of the simulated virtual space, multi-directional vibration is applied to the titanium alloy forging to obtain the primary response flow of the titanium alloy forging;

[0084] Time-frequency domain analysis was performed on the primary response flow to obtain various dynamic indicators of the titanium alloy forging.

[0085] The dynamic response data of the titanium alloy forging is obtained by aligning the various dynamic indicators with timestamps.

[0086] In this embodiment of the invention, the response acquisition channel based on simulated virtual space applies multi-directional vibration to the titanium alloy forging to obtain the primary response flow of the titanium alloy forging, including:

[0087] Based on the geometric configuration data in the initial state data, virtual measuring points are defined on the titanium alloy forging.

[0088] Based on the virtual measuring points, construct a response data acquisition network connecting the virtual measuring points;

[0089] Based on the response data acquisition network, the independent vibration command sequence is applied to the titanium alloy forging to obtain the original response signal of the titanium alloy forging;

[0090] The original response signal is subjected to integrity verification to obtain the primary response flow of the titanium alloy forging.

[0091] Specifically, when performing modal decoupling on multi-dimensional vibration control parameters to obtain an independent vibration command sequence for titanium alloy forgings, the following steps are first taken: First, the content of the multi-dimensional vibration control parameters is clarified. These parameters encompass vibration frequency, amplitude, and duration in different vibration directions, and these parameters may be correlated or coupled. Then, based on the geometric configuration and material property data of the titanium alloy forgings, the coupling mechanism between parameters in different vibration directions is analyzed to determine the specific ways and degrees of mutual influence between parameters in each vibration direction. Next, a physical decomposition method is used to separate the coupled vibration parameters according to the vibration direction. For each vibration direction, based on the structural characteristics and material properties of the forging in that direction, parameters such as vibration frequency, amplitude, and duration are independently adjusted to ensure that the vibration parameters in each direction correspond only to vibration in a single direction and do not interfere with vibration parameters in other directions. Finally, the adjusted independent parameters in each vibration direction are organized according to a preset command format to form independent vibration commands for different vibration directions. All these independent vibration commands together constitute the independent vibration command sequence for the titanium alloy forgings.

[0092] Furthermore, based on the response acquisition channels in the simulated virtual space, when applying multi-directional vibration to the titanium alloy forging to obtain the primary response flow, a three-dimensional virtual model completely identical to the actual titanium alloy forging is first constructed in the simulated virtual space according to the geometric configuration data in the initial state data of the titanium alloy forging. This ensures that the structural shape, size, and connection relationships of each part of the virtual model are the same as those of the actual forging. Then, according to the structural characteristics of the forging and the key monitoring locations of the vibration response, response acquisition channels are set on the virtual model. These channels need to cover the parts of the forging that are prone to stress concentration, structurally weak parts, and vibration-sensitive parts. Each acquisition channel corresponds to a specific monitoring point, which can capture the physical changes of that monitoring point in real time during the vibration process. Next, the previously obtained independent vibration command sequence is input into the vibration control module of the simulated virtual space. The vibration control module applies vibration to the virtual model in different directions such as the X-axis, Y-axis, and Z-axis according to the requirements of each independent vibration command in the command sequence, ensuring that the vibration action in each direction strictly follows the vibration frequency, amplitude, and vibration duration in the corresponding command. During the vibration application process, each response acquisition channel collects the physical change signals of the corresponding monitoring points in real time, and these signals are continuously recorded in the order of acquisition time to form a continuous signal stream. Finally, the recorded signal stream is initially screened to remove invalid signals caused by acquisition channel failure or interference factors, and the primary response stream of the titanium alloy forging containing effective vibration response signals is obtained.

[0093] Furthermore, when performing time-frequency domain analysis on the primary response flow to obtain various dynamic indicators of titanium alloy forgings, all signals in the primary response flow are first acquired. These signals are physical quantity data of different monitoring points changing with time during vibration. In terms of time domain analysis, for the signal at each monitoring point, the maximum and minimum values ​​of the signal are statistically analyzed over the entire vibration duration, the average value of the signal is calculated, and the trend of signal change with time is observed. The time points when the signal reaches its peak and the time periods when the signal remains stable are recorded. In terms of frequency domain analysis, the frequency range for analysis is determined based on the signal acquisition time interval. The time domain signal is converted into a frequency domain signal, the main frequency components contained in the signal are identified, the amplitude of each main frequency component is calculated, the proportion of different frequency components in the entire signal is analyzed, and the existence of resonant frequencies is determined. Then, the maximum, minimum, average, and time change trend data obtained from the time domain analysis are classified and organized with the main frequency components, amplitudes of each frequency, frequency proportions, and resonant frequencies obtained from the frequency domain analysis. The time domain-related data are classified into one type of dynamic indicator, and the frequency domain-related data are classified into another type of dynamic indicator. These different categories of data together constitute various dynamic indicators of titanium alloy forgings.

[0094] Furthermore, when aligning multiple dynamic indicators with timestamps to obtain the dynamic response data of the titanium alloy forging, the timestamp information corresponding to each type of dynamic indicator is first extracted. The timestamp information records the signal acquisition time corresponding to the dynamic indicator. For example, the timestamp of a certain time-domain displacement indicator is "2 seconds after vibration starts", and the timestamp of a certain frequency-domain amplitude indicator is "5 seconds after vibration starts". Subsequently, a unified time reference is determined, with the moment when the titanium alloy forging begins to receive vibration as the starting time point. The timestamps of all dynamic indicators are converted into absolute time values ​​based on this starting time point. For example, "2 seconds after vibration starts" is converted into absolute time values. "2 seconds" is converted to "2 seconds", and "5 seconds after vibration starts" is converted to "5 seconds". Next, all dynamic indicators are sorted according to the order of their absolute time values. For different types of dynamic indicators with the same absolute time value, they are grouped into dynamic indicator groups under the same time node. For those with slight differences in absolute time values, it is ensured that each time node contains various types of dynamic indicators at the corresponding time. Finally, the sorted and aligned time nodes and corresponding dynamic indicator groups are integrated in chronological order to form structured data with time as the axis, containing multiple types of dynamic indicators at each time. This structured data is the dynamic response data of titanium alloy forgings.

[0095] Specifically, when defining virtual measuring points on a titanium alloy forging based on the geometric configuration data in the initial state data, the complete geometric configuration data is first extracted from the initial state data. This data includes information such as the three-dimensional dimensions, structural shape, and overall structural layout of the titanium alloy forging. Next, the stress distribution that may occur during vibration of the forging is analyzed, and the areas that need to be monitored are determined based on the characteristics of the geometric configuration, such as locations where structural dimensions change abruptly, areas prone to stress concentration, and key functional parts of the forging. Then, within these key monitoring areas, specific virtual measuring point positions are set according to the principle of uniform distribution and comprehensive coverage of regional characteristics. Each virtual measuring point needs to have its specific coordinates in the three-dimensional coordinate system of the forging clearly defined to ensure that each measuring point can accurately correspond to a specific position on the forging. This is how the definition of virtual measuring points on the titanium alloy forging is completed.

[0096] Furthermore, when constructing a response data acquisition network connecting virtual measurement points, all defined virtual measurement points are first identified, clarifying the location coordinates and required response data types for each point. Then, data transmission paths are planned, and based on the spatial distance between measurement points and the structural characteristics of the forging, the principle of proximity is adopted to connect adjacent virtual measurement points via virtual data transmission lines, forming basic measurement point connection units. For measurement points that are far apart but require collaborative data acquisition, virtual data relay nodes are set up to facilitate data transmission between these measurement points, ensuring that all measurement points can access the network. Simultaneously, virtual data aggregation nodes are set up in the acquisition network. Response data collected by all virtual measurement points is aggregated to the aggregation node via transmission lines or relay nodes. The aggregation node is responsible for initial data reception and temporary storage. In addition, each virtual measurement point is configured with unique identification information, which is associated with its location coordinates and data type, ensuring accurate identification of the measurement point corresponding to each data point during data transmission. Through these steps, a response data acquisition network connecting all virtual measurement points is constructed.

[0097] Furthermore, when applying independent vibration command sequences to titanium alloy forgings based on the response data acquisition network to obtain the original response signal, the previously obtained independent vibration command sequences are first parsed to clarify the vibration direction, vibration parameters, and execution order of each command. Then, the parsed vibration commands are sent to the vibration execution module in the simulated virtual space. The vibration execution module applies vibration to the virtual model of the titanium alloy forging in the corresponding vibration direction according to the command requirements. The application process strictly follows the vibration frequency, amplitude, and vibration duration in the command, and completes the vibration application in each direction in the order of command sequence. At the same time as applying vibration, the response data acquisition network is activated. Each virtual measuring point in the network captures the physical response changes at the corresponding location in real time and sends the captured response data to the data aggregation node through a preset transmission path. The aggregation node classifies and stores all received response data according to the acquisition time and measuring point identification. This unprocessed data containing the response information of all measuring points is the original response signal of the titanium alloy forging.

[0098] Furthermore, when performing integrity verification on the original response signal to obtain the primary response stream, the integrity verification criteria are first clarified, including two aspects: first, whether all virtual measuring points have corresponding response data, i.e., no missing measuring point data; second, whether the response data of each measuring point covers the entire vibration duration, i.e., no data gaps. Then, the original response signal is checked one by one according to the above criteria. First, the number of measuring point identifiers contained in the original response signal is counted and compared with the total number of defined virtual measuring points. If there are missing identifiers, it is determined that the data of the corresponding measuring point is missing, and the vibration simulation and data acquisition in the area where the measuring point is located need to be retried until the response data of the measuring point is obtained. Then, for the response data of each measuring point, it is checked whether the corresponding time record is continuous and whether it covers the entire time period from the start to the end of the vibration. If there are time gaps, the cause of the gaps is analyzed, and the corresponding data is reacquired according to the gap time period. After all the missing data is supplemented, the original response signals that have passed the verification are organized in the order of acquisition time to form a continuous signal stream containing complete response information of all measuring points. This signal stream is the primary response stream of the titanium alloy forging.

[0099] In summary, modal decoupling of multi-dimensional vibration control parameters to obtain independent vibration command sequences can avoid mutual interference between different vibration modes, ensuring that each vibration command can accurately act on the corresponding area of ​​the forging, providing a foundation for the accurate application of subsequent multi-directional vibrations and reducing control errors caused by modal coupling. Defining virtual measuring points based on the geometric configuration data in the initial state data allows the measuring point positions to accurately match the geometric features of the forging, covering areas where stress is easily concentrated or critical, avoiding blind placement of measuring points, and ensuring the relevance and effectiveness of subsequent data acquisition.

[0100] In summary, constructing a response data acquisition network based on virtual measuring points enables the synchronous acquisition of response signals from multiple parts of the forging, forming a comprehensive data acquisition system. This avoids the limitations of data from a single measuring point and provides more complete raw data support for subsequent analysis. Applying independent vibration command sequences and acquiring raw response signals followed by integrity verification can eliminate incomplete or abnormal data, ensuring the accuracy and reliability of the primary response stream and preventing invalid data from interfering with subsequent time-frequency domain analysis results.

[0101] In summary, time-frequency domain analysis of the primary response flow yields multiple dynamic indices, enabling the analysis of the vibration response characteristics of forgings from both time and frequency dimensions. This reveals stress variation patterns across different frequency bands, providing multi-dimensional data for evaluating residual stress reduction effectiveness. Timestamp alignment of these dynamic indices eliminates time-dimensional discrepancies, ensuring their correlation at the same time point and resulting in more consistent dynamic response data. This lays a precise data foundation for subsequent multimodal data fusion and residual stress assessment index calculation.

[0102] S3. Perform multimodal data fusion on the dynamic response data to obtain the residual stress reduction evaluation index of the titanium alloy forging;

[0103] In this embodiment of the invention, the step of performing multimodal data fusion on the dynamic response data to obtain the residual stress reduction evaluation index of the titanium alloy forging includes:

[0104] The dynamic response data is subjected to signal integrity verification to obtain the verified dynamic response data of the titanium alloy forging.

[0105] Empirical mode decomposition is performed on the verified dynamic response data to obtain the intrinsic mode components of the titanium alloy forging.

[0106] Based on the sample entropy of the intrinsic mode components, construct the weighted fusion matrix of the intrinsic mode components;

[0107] Based on the weighted fusion matrix, the residual stress reduction assessment index is calculated, wherein the calculation formula for the residual stress reduction assessment index is:

[0108] ;

[0109] in, This represents the residual stress reduction assessment index. This represents the total number of the intrinsic modal components. Indicates the first The weights of the intrinsic mode components. This represents the total number of data points for each of the intrinsic mode components. Indicates the first The intrinsic mode components are at time... Quantity, Indicates the first The average value of each intrinsic mode component.

[0110] In this embodiment of the invention, constructing the weighted fusion matrix of the intrinsic mode components based on the sample entropy of the intrinsic mode components includes:

[0111] Based on a preset weight range, the sample entropy is reconstructed to obtain the initial weights of the titanium alloy forging.

[0112] The initial weights are normalized to obtain the final weights of the titanium alloy forgings.

[0113] The final weights are assigned to the intrinsic mode components according to the corresponding relationship to form a weighted fusion matrix of the intrinsic mode components.

[0114] Specifically, when performing signal integrity verification on dynamic response data to obtain verified dynamic response data, the composition of dynamic response data is first clarified. It consists of multiple types of dynamic index data integrated along the time axis after timestamp alignment, including response information such as displacement, velocity, and acceleration of different virtual measuring points at various times. During the verification process, the continuity of data is checked first. The dynamic response data is examined segment by segment according to the time sequence to confirm whether there is a situation where data is completely missing or some measuring point data is interrupted within a certain time period. If data is missing, the process is traced back to the data acquisition stage to check whether it is caused by a temporary failure of the response acquisition network or signal transmission delay. For the missing part, the backup data of the corresponding time period in the simulated virtual space is retrieved to supplement it. Next, the rationality of the data is checked. Based on the material properties and geometric characteristics of the titanium alloy forging, it is determined whether the response data of each measuring point is within a reasonable range. For example, if the displacement data of a certain measuring point far exceeds the maximum displacement value that the material's elastic deformation can withstand, it is judged as abnormal data. After removing the abnormal data, the valid data at the corresponding time is re-acquired. After all data continuity and rationality issues are resolved, verified dynamic response data without gaps or abnormalities is formed.

[0115] Furthermore, when performing empirical mode decomposition on the calibrated dynamic response data to obtain intrinsic modal components, the core is to decompose the complex dynamic response signal into several simple vibration modes with physical meaning. First, the complete response signal of a certain measuring point is extracted from the calibrated dynamic response data, and the local maxima and local minima of the signal are determined. Cubic spline interpolation is used to connect all local maxima to form an upper envelope, and all local minima to form a lower envelope, ensuring that the upper envelope completely covers the peak portion of the signal, and the lower envelope completely covers the valley portion. Next, the average values ​​of the upper and lower envelopes at each time point are calculated to obtain the average envelope. The original response signal is then subtracted from this average envelope to obtain the intermediate signal. Finally, it is checked whether the intermediate signal satisfies the intrinsic modal component requirement. The two conditions for intrinsic modal components are: first, the number of local maxima and local minima of the signal are equal or differ by no more than 1; second, at any given time, the average value of the upper and lower envelopes of the signal is 0. If the conditions are not met, the intermediate signal is used as the new original signal, and the steps of finding extreme points, constructing envelopes, calculating average envelopes, and subtracting average envelopes are repeated until intrinsic modal components that meet the conditions are obtained. The first intrinsic modal component is separated from the original response signal, and the entire decomposition process is repeated for the remaining signal to obtain the second, third, ..., Nth intrinsic modal components in sequence, until the remaining signal can no longer be decomposed into intrinsic modal components that meet the conditions. All the decomposed intrinsic modal components that meet the conditions are the intrinsic modal components of the titanium alloy forging.

[0116] Furthermore, when constructing a weighted fusion matrix based on the sample entropy of the intrinsic mode components (IMCs), the sample entropy is used to measure the complexity of the IMC signal. The more complex the signal, the larger the sample entropy value, and the richer the effective information contained in the component. First, the sample entropy of each IMC is calculated. A continuous data segment from each IMC is selected as the analysis sequence. Based on the characteristics of the dynamic response signal of titanium alloy forgings, the embedding dimension and similarity tolerance are pre-set. The analysis sequence is reconstructed into multiple vectors of corresponding dimensions according to the set embedding dimension. The Euclidean distance between each vector and all other vectors is calculated. The number of vector pairs with a distance less than the similarity tolerance is counted to obtain the proportion of similar vector pairs to the total number of vector pairs. Then, the embedding dimension is increased by 1, and the above steps of reconstructing vectors, calculating distances, and counting the proportion of similar vectors are repeated to obtain a new... The similarity vector ratio is calculated first; then, by calculating the negative natural logarithm of the ratio of the new similarity vector ratio to the original similarity vector ratio, the sample entropy of the intrinsic mode component is obtained. After calculating the sample entropy of all intrinsic mode components in the same way, a preset weight interval is set according to the correlation between sample entropy and information importance. Each sample entropy value is mapped to the corresponding weight interval to obtain the initial weight of each intrinsic mode component. All initial weights are normalized, and the sum of all initial weights is calculated. Each initial weight is divided by the sum to obtain the final weight of each intrinsic mode component, ensuring that the sum of all final weights is 1. Finally, each intrinsic mode component is mapped one-to-one with its corresponding final weight, and the mapping relationship between "intrinsic mode component - final weight" is arranged into a matrix. This matrix is ​​the weighted fusion matrix of the intrinsic mode components.

[0117] Furthermore, when calculating the residual stress reduction evaluation index based on the weighted fusion matrix, the final weight of each intrinsic modal component and the corresponding intrinsic modal component data are first extracted from the weighted fusion matrix. For each intrinsic modal component, its value at all acquisition times is obtained, and the average value of all data points for that intrinsic modal component is calculated by summing the values ​​at all times and dividing by the total number of data points. Then, the contribution value of that intrinsic modal component is calculated by first calculating the square of the absolute value of the difference between the value at each time and the average value, and then summing the squared values ​​at all times. After summing the values ​​and dividing by the total number of data points, we obtain the variance class value of the component. Then, we calculate the weight ratio of the component. Since normalization has been performed previously, the sum of the final weights of all intrinsic modal components is 1. Therefore, the weight ratio of the component is its final weight. Multiply the weight ratio by the variance class value to obtain the contribution value of the intrinsic modal component to the residual stress reduction evaluation index. Then, we sum the contribution values ​​of all intrinsic modal components to obtain the total contribution value. Taking the square root of the total contribution value gives us the residual stress reduction evaluation index for titanium alloy forgings.

[0118] Specifically, when reconstructing information from sample entropy based on a preset weight interval to obtain the initial weights of the titanium alloy forging, it is first clarified that the preset weight interval is pre-set based on the correlation between sample entropy and the importance of intrinsic modal component information. Different sample entropy value ranges correspond to different weight intervals. For example, intervals with larger sample entropy values ​​correspond to higher weight intervals, and intervals with smaller sample entropy values ​​correspond to lower weight intervals. The core logic of this setting is that the larger the sample entropy, the higher the signal complexity of the intrinsic modal components, and the richer the effective information related to residual stress reduction, thus a higher weight interval should be assigned. Next, the sample entropy value of each intrinsic modal component is obtained one by one, and each sample entropy value is matched with the preset weight interval to determine the weight of the intrinsic modal component. The specific weight range to which the sample entropy value belongs is determined. For example, if the sample entropy value of a certain intrinsic modal component is 0.8, and the preset weight range "0.7-0.9" corresponds to the weight range "0.6-0.8", then the weight range corresponding to this sample entropy is determined to be "0.6-0.8". Then, within the determined weight range, combined with the dynamic response data characteristics corresponding to this intrinsic modal component, a specific weight value is selected as the initial weight of this intrinsic modal component. For example, within the weight range "0.6-0.8", if this intrinsic modal component is highly sensitive to changes in residual stress, then 0.75 is selected as its initial weight. In this way, the initial weights of all intrinsic modal components are determined, and the initial weights of the titanium alloy forging are obtained.

[0119] Furthermore, when normalizing the initial weights to obtain the final weights of the titanium alloy forgings, the sum of the initial weights of all intrinsic modal components is first calculated. The initial weight of each intrinsic modal component is then divided by this sum to obtain the proportion of each initial weight in the total weight. For example, if the sum of the initial weights of all intrinsic modal components is 5, and the initial weight of a certain intrinsic modal component is 1, then the proportion of that initial weight is 1 / 5 = 0.2. Each proportion calculated in this way is the weight after normalization, and the sum of all normalized weights is 1. These normalized weights are the final weights of the titanium alloy forgings.

[0120] Furthermore, when assigning the final weights to the intrinsic modal components according to the corresponding relationship to form the weighted fusion matrix of the intrinsic modal components, firstly, a one-to-one correspondence between each intrinsic modal component and its corresponding final weight is established to ensure that each intrinsic modal component has one and only one exclusive final weight, and each final weight clearly corresponds to one intrinsic modal component. For example, intrinsic modal component 1 corresponds to a final weight of 0.2, intrinsic modal component 2 corresponds to a final weight of 0.3, and so on. Next, according to the matrix format requirements, the identification information of the intrinsic modal components is used as the rows or columns of the matrix, and the corresponding final weight is used as the value at the intersection position with the identification information in the matrix. For example, the first row and first column of the matrix corresponds to the identification of intrinsic modal component 1, and the first row and second column corresponds to its final weight of 0.2; the second row and first column corresponds to the identification of intrinsic modal component 2, and the second row and second column corresponds to its final weight of 0.3, and so on. All intrinsic modal components and their corresponding final weights are filled into the matrix, and the complete matrix formed is the weighted fusion matrix of the intrinsic modal components.

[0121] Specifically, the total number of intrinsic modal components comes from the result of empirical mode decomposition on the verified dynamic response data. Empirical mode decomposition decomposes the verified dynamic response data into multiple intrinsic modal components. The number of components obtained after decomposition is the total number of intrinsic modal components.

[0122] Furthermore, the first The weights of each intrinsic mode component (EMC) are derived from the process of constructing a weighted fusion matrix based on the sample entropy of the EMC. First, the sample entropy is reconstructed based on a preset weight interval to obtain initial weights. Then, the initial weights are normalized to obtain final weights. These final weights are then assigned to each EMC according to their corresponding relationships. The final weight of the eigenmode component is the th The weights of each intrinsic mode component.

[0123] Furthermore, the total number of data points for each intrinsic mode component is obtained by statistically analyzing the data points of each intrinsic mode component obtained through empirical mode decomposition. The total number of data points contained in each intrinsic mode component is the total number of data points for each intrinsic mode component.

[0124] Furthermore, the first Each intrinsic mode component at time... The number is obtained by performing empirical mode decomposition on the verified dynamic response data. After identifying each intrinsic mode component, the time step is extracted from the time series data of that intrinsic mode component. The corresponding specific value, this value is the number Each intrinsic mode component at time... The quantity.

[0125] Furthermore, the first The average value of the eigenmode components is the eigenmode component of the eigenmode. The number of data points contained in the eigenmode component is calculated by taking the eigenmode component as an example. The sum of the counts of each intrinsic mode component at each time step is used to obtain the total number of data points for that intrinsic mode component. This sum is then divided by the total number of data points for that intrinsic mode component to obtain the result of the calculation. The average value of each intrinsic mode component.

[0126] Furthermore, the significance of this formula is to comprehensively consider the influence of each intrinsic modal component on the residual stress reduction effect, and to calculate an index that can evaluate the residual stress reduction of titanium alloy forgings. Specifically, the weight ratio of each intrinsic modal component is first calculated, then the average of the squares of the difference between the number of data points of each intrinsic modal component at each time point and the average value of that component is calculated, then the weight ratio of each intrinsic modal component is multiplied by the average of the squares of its corresponding difference, and finally the square root of the sum of all multiplication results is taken. The result is the residual stress reduction evaluation index, which can be used to judge the effect of residual stress reduction in titanium alloy forgings.

[0127] Furthermore, when the first When the weight of the eigenmode component increases, if other parameters remain unchanged, the proportion of that component's weight will increase, thus increasing the multiplication result. The sum of all multiplication results may increase, and ultimately, the residual stress reduction evaluation index may increase. Each intrinsic mode component at time... When the difference between the number of data points and the average value of a component increases, the square of the difference increases, which in turn increases the average value of the squared differences of that component. This may increase the multiplication result, the sum of all multiplication results, and ultimately, the residual stress reduction assessment index. Conversely, when the total number of data points for each intrinsic modal component changes, if the sum of the differences between the number of data points and the average value at each time point remains constant, an increase in the total number of data points will decrease the average value of the squared differences, potentially decreasing the multiplication result, the sum of all multiplication results, and ultimately, the residual stress reduction assessment index. Furthermore, when the total number of intrinsic modal components increases, if the multiplication result of the newly added component is positive, the sum of all multiplication results may increase, and ultimately, the residual stress reduction assessment index may increase. If the multiplication result of the newly added component is negative, the sum of all multiplication results may decrease, and ultimately, the residual stress reduction assessment index may decrease.

[0128] In summary, signal integrity verification of dynamic response data can eliminate distortions and missing information generated during data transmission or acquisition, ensuring the accuracy and integrity of the verified dynamic response data, avoiding invalid data from interfering with subsequent analysis, and laying a reliable data foundation for the accurate calculation of residual stress reduction assessment indicators. Empirical mode decomposition (EMD) of the verified data yields intrinsic modal components, which can decompose complex dynamic response signals into multiple physically meaningful single modal components. Each component corresponds to the stress response characteristics of the forging at different frequency bands, enabling refined analysis of complex signals and facilitating subsequent targeted analysis of the correlation between each mode and residual stress reduction.

[0129] In summary, a weighted fusion matrix is ​​constructed based on the sample entropy of the intrinsic modal components. The sample entropy can reflect the complexity and information value of the components. By allocating weights accordingly, components with high information content and more representative significance for residual stress reduction can be given higher weights, avoiding evaluation bias caused by treating all components equally and improving the effectiveness of the fused data.

[0130] In summary, based on the weighted fusion matrix, the residual stress reduction evaluation index is calculated using a formula. The weight ratio in the formula is combined with the degree of fluctuation of the modal components, which not only reflects the difference in contribution of different modes, but also quantifies the stress change of each mode through the mean square error. Finally, the comprehensive evaluation index is obtained by integrating it in the form of square root, realizing the quantitative and accurate characterization of the residual stress reduction effect, and providing a clear basis for subsequent parameter optimization.

[0131] In summary, reconstructing sample entropy based on a preset weight range to obtain initial weights can filter out meaningless extreme values ​​or abnormal information in the sample entropy through range constraints, ensuring that the initial weights are always within a reasonable and effective range. This avoids the weight allocation deviating from actual needs due to excessive fluctuations in sample entropy data, providing a stable foundation for subsequent weight calculations. Normalizing the initial weights to obtain the final weights can eliminate the weight order interference caused by differences in sample entropy values ​​of different intrinsic mode components, ensuring that the final sum of the weights of all components meets the standardization requirements, guaranteeing the comparability of the weight proportions of each component, and avoiding distortion in the calculation of the fusion matrix due to inconsistent weight order.

[0132] In summary, assigning the final weights to the intrinsic modal components according to their corresponding relationships to form a weighted fusion matrix can establish a precise correlation between the weights and the modal components, clarify the contribution ratio of each intrinsic modal component in the subsequent calculation of residual stress reduction assessment indicators, ensure that the fusion matrix can accurately reflect the differences in information value of each mode, provide a structured and directly applicable weight basis for subsequent quantitative assessment, and improve the standardization and accuracy of the assessment process.

[0133] S4. Based on the residual stress reduction evaluation index, perform multi-objective decision-making on the multi-dimensional vibration control parameters to obtain the optimized vibration parameters of the titanium alloy forging.

[0134] In this embodiment of the invention, the step of performing multi-objective decision-making on the multi-dimensional vibration control parameters based on the residual stress reduction evaluation index to obtain the optimized vibration parameters of the titanium alloy forging includes:

[0135] The residual stress reduction evaluation index is standardized in multiple dimensions to obtain the standardized evaluation index of the titanium alloy forging.

[0136] Based on the standardized evaluation index, the multi-dimensional vibration control parameters are prioritized to obtain the degree of influence of the multi-dimensional vibration control parameters on the reduction of residual stress in the titanium alloy forging.

[0137] Based on the degree of influence, a multi-objective trade-off analysis is performed on the multi-dimensional vibration control parameters to obtain the preliminary optimized parameters of the titanium alloy forging.

[0138] The initial optimized parameters were verified for consistency to obtain the optimized vibration parameters of the titanium alloy forging.

[0139] In this embodiment of the invention, prioritizing the multi-dimensional vibration control parameters based on the standardized evaluation index to obtain the degree of influence of the multi-dimensional vibration control parameters on the reduction of residual stress in the titanium alloy forging includes:

[0140] The key features in the multi-dimensional vibration control parameters are analyzed to obtain the parameter feature set of the multi-dimensional vibration control parameters;

[0141] Correlation analysis is performed on the parameter feature set to obtain similarity characteristic data of the multi-dimensional vibration control parameters;

[0142] Based on the correspondence between the similarity characteristic data and the standardized evaluation indicators, the multi-dimensional vibration control parameters are comprehensively evaluated to obtain the degree of influence of the multi-dimensional vibration control parameters on the reduction of residual stress in the titanium alloy forging.

[0143] Specifically, when standardizing the residual stress reduction assessment indicators to obtain standardized assessment indicators for titanium alloy forgings, the first step is to clarify the multiple dimensions covered by the residual stress reduction assessment indicators. These dimensions are all directly related to the residual stress reduction effect of titanium alloy forgings and may include specific indicators reflecting the degree of stress reduction, stress distribution uniformity, vibration response stability, etc. Different dimensions of indicators have different numerical units and ranges due to differences in the measurement objects and calculation methods. To eliminate the interference of these differences on subsequent parameter analysis, a unified standardization rule needs to be set for each dimension of the indicators: a larger indicator value represents a greater residual stress reduction. For dimensions with better performance, the minimum and maximum values ​​of the indicator in historical data or theoretical calculations are used as benchmarks. The actual value of a specific indicator under that dimension is subtracted from the minimum value, and then divided by the difference between the maximum and minimum values ​​to obtain the standardized value of the indicator. For dimensions where a smaller indicator value indicates a better residual stress reduction effect, the maximum and minimum values ​​of the indicator under that dimension are used as benchmarks. The maximum value is subtracted from the actual value of a specific indicator under that dimension, and then divided by the difference between the maximum and minimum values ​​to obtain the standardized value of the indicator. By processing the residual stress reduction evaluation indicators of all dimensions one by one through the above rules, a standardized evaluation indicator with a unified numerical scale for all dimensions is finally obtained.

[0144] Furthermore, when prioritizing multi-dimensional vibration control parameters based on standardized evaluation indicators to determine their impact on residual stress reduction, the specific composition of these parameters is first clarified. These parameters, obtained through multi-physics field coupling vibration control, include vibration frequency, vibration amplitude, vibration direction, and vibration duration—parameters directly related to vibration control. Next, for each vibration control parameter, the changes in standardized evaluation indicators under different values ​​are analyzed. For example, keeping other vibration control parameters constant and only changing the vibration frequency, the magnitude of change in each dimension's standardized evaluation indicator corresponding to different frequency values ​​is recorded. The larger the magnitude of change, the more significant the impact of that vibration control parameter on residual stress reduction. Similarly, the impact of each other vibration control parameter—vibration amplitude, vibration direction, vibration duration, etc.—on the standardized evaluation indicators is analyzed. Then, the parameters are ranked according to their overall impact on the standardized evaluation indicators, with the priority of parameters decreasing from largest to smallest. This ranking clarifies the impact of each multi-dimensional vibration control parameter on residual stress reduction in titanium alloy forgings.

[0145] Furthermore, when conducting a multi-objective trade-off analysis of the multi-dimensional vibration control parameters based on the degree of influence to obtain the preliminary optimized parameters for titanium alloy forgings, the specific content of the multi-objectives is first determined. These objectives are set around the residual stress reduction effect of titanium alloy forgings and actual production needs, including core objectives such as "maximizing the degree of residual stress reduction," "maximizing the uniformity of stress distribution," "minimizing vibration energy consumption," and "avoiding structural damage to forgings." Subsequently, according to the order of the degree of influence of the vibration control parameters from high to low, each parameter is adjusted and analyzed in turn: the parameter with the highest degree of influence is adjusted first, and multiple candidate values ​​are selected within the reasonable range of this parameter, and simulations are performed respectively. For each candidate value, the achievement of each objective is recorded, and the candidate value that enables most objectives to be at a relatively good level is recorded. Then, based on the candidate value, the parameter with the next lower degree of influence is adjusted, and multiple candidate values ​​are selected for simulation to analyze their supplementary influence on each objective. Candidate values ​​that can further optimize the objective achievement effect are then selected. Following the above logic, all vibration control parameters are adjusted and simulated in sequence. If the adjustment of a certain parameter causes a certain key objective to deteriorate, the adjustment plan is abandoned. Finally, a set of vibration control parameters that enables all objectives to meet the expected requirements and has the best overall effect is selected. This set is the preliminary optimization parameters for titanium alloy forgings.

[0146] Furthermore, when performing consistency verification on the preliminary optimization parameters to obtain the optimized vibration parameters for the titanium alloy forging, the core requirements for consistency verification must be clarified first: First, the vibration control parameters in the preliminary optimization parameters must be logically consistent and there should be no contradictions. That is, the combination of values ​​for each parameter must conform to the physical laws of vibration control of titanium alloy forging. For example, the combination of vibration frequency and vibration duration must ensure that the forging has sufficient time to respond to vibration and release stress, avoiding insufficient stress release due to excessively high frequency but insufficient duration. Second, the preliminary optimization parameters must match the initial state data of the titanium alloy forging. For example, for thin-walled forgings, the initial... The amplitude in the optimized parameters must be controlled within the allowable range of material elastic deformation to avoid excessive amplitude leading to structural deformation. Based on the above requirements, the following verification is performed: First, check the logical relationship between each parameter and compare the parameter combination with the basic physical laws of titanium alloy vibration control. If there is a contradiction, adjust the parameters. Then, combine the initial state data of the forging to verify whether the parameters are suitable. If a parameter does not match the initial state data, adjust the value of that parameter. After all contradictions and mismatches are resolved, confirm again that the residual stress reduction effect corresponding to the adjusted parameter combination still meets the target requirements. The parameter combination obtained at this time is the optimized vibration parameter of the titanium alloy forging.

[0147] Specifically, when performing parameter analysis on the key features of multi-dimensional vibration control parameters to obtain the parameter feature set, the composition of the multi-dimensional vibration control parameters is first clarified, which includes parameters directly related to the vibration control of titanium alloy forgings, such as vibration frequency, vibration amplitude, vibration direction combination, and vibration duration. Next, key features are extracted for each parameter: for vibration frequency, key features include the frequency range, the step size of frequency change, and the duration of frequency stability; for vibration amplitude, key features include the maximum peak value, the average amplitude value, and the amplitude change trend over time; for vibration direction combination, key features include the number of directions involved in the vibration, the initiation sequence of vibration in each direction, and the intensity ratio of vibration in each direction; for vibration duration, key features include the total vibration duration, the segment duration of each vibration stage, and the interval duration between adjacent vibration stages. All the key features of all parameters are systematically organized and categorized in the form of "parameter type - key feature name - specific feature content," forming a complete set, which is the parameter feature set of the multi-dimensional vibration control parameters.

[0148] Furthermore, when conducting correlation analysis on the parameter feature set to obtain similarity characteristic data of multi-dimensional vibration control parameters, the dimensions of the correlation analysis are first determined, including the similarity of parameter feature value ranges, the similarity of variation trends, and the similarity of functional effects. Regarding the similarity of value ranges, the value intervals of different parameter features are compared; for example, the vibration frequency range is 50-150Hz, and the vibration amplitude range is 0.1-0.5mm. The degree of overlap and the proportional relationship of the interval span are calculated to determine the similarity of the value ranges. Regarding the similarity of variation trends, the changes in different parameter features over time are analyzed. The variation patterns are analyzed, such as the linear increase in vibration frequency over time and the stepwise increase in vibration amplitude over time. By comparing the shape and rate of change of the two curves, the similarity of the variation trends can be determined. Regarding the similarity of functional effects, the influence of different parameter characteristics on the vibration effect is evaluated. For example, both increasing the vibration frequency and increasing the vibration amplitude can enhance the disturbance effect of internal stress in the forging, and the similarity of their functional effects can be judged. The similarity analysis results of all dimensions are quantified and recorded, and the resulting dataset containing the similarity relationships of each parameter characteristic is the similarity characteristic data of multi-dimensional vibration control parameters.

[0149] Furthermore, when comprehensively evaluating multi-dimensional vibration control parameters based on the correspondence between similarity characteristic data and standardized evaluation indicators to determine their impact on residual stress reduction, the first step is to establish a correspondence between similarity characteristic data and standardized evaluation indicators. For example, if the similarity characteristic data of two sets of parameter features are labeled "high similarity," then the changes in the standardized evaluation indicators corresponding to these two sets of parameter features are examined. If the standardized evaluation indicators corresponding to highly similar parameter features show consistent trends and similar magnitudes, it indicates that the impact of this type of parameter feature on residual stress reduction is consistent. If the similarity characteristic data of parameter features are labeled "low similarity," the trends in the corresponding standardized evaluation indicators differ significantly. This indicates that different types of parameter characteristics have significantly different effects on residual stress reduction. Next, for each multi-dimensional vibration control parameter, based on its classification in similar characteristic data and the magnitude of change in the standardized evaluation index corresponding to that classification, the magnitude of the parameter's impact on residual stress reduction is determined: if the magnitude of change in the standardized evaluation index corresponding to a parameter's characteristic classification is large, then the parameter is considered to have a high degree of impact on residual stress reduction; if the magnitude of change in the standardized evaluation index corresponding to a parameter's characteristic classification is small, then the parameter is considered to have a low degree of impact on residual stress reduction. Through the evaluation of all multi-dimensional vibration control parameters one by one, the degree of impact of each parameter on the residual stress reduction of titanium alloy forgings is clarified.

[0150] In summary, multi-dimensional standardization of residual stress reduction assessment indicators can eliminate differences in dimensions and numerical ranges between different dimensions, avoid bias towards dimensions with larger numerical values ​​due to different indicator magnitudes, and ensure that the standardized assessment indicators have a unified and comparable benchmark. This provides a fair and objective data basis for subsequent parameter priority allocation and ensures that the assessment results are not affected by the data format.

[0151] In summary, prioritizing multi-dimensional vibration control parameters based on standardized evaluation indicators can accurately identify parameters that have a more significant impact on residual stress reduction through correlation analysis between indicators and parameters, clarify the order of importance of each parameter, avoid spreading efforts evenly in parameter optimization, and allow subsequent control resources and energy to be focused on key parameters, thereby improving optimization efficiency.

[0152] In summary, conducting multi-objective trade-off analysis based on the degree of parameter influence to obtain preliminary optimized parameters can meet the core requirement of residual stress reduction while taking into account the synergy and constraints between parameters. This avoids the failure of other parameters due to the pursuit of optimization of a single parameter, achieves balanced optimization among multiple parameters, and ensures that the preliminary optimized parameters meet the multi-objective control requirements in actual production.

[0153] In summary, consistency verification of preliminary optimized parameters can check for logical conflicts or contradictory values ​​among parameters, eliminate parameter combinations that do not conform to process constraints, equipment capabilities, or physical laws, ensure that the final optimized vibration parameters are feasible and stable, avoid the failure of subsequent vibration control due to parameter inconsistencies, and ensure the smooth implementation and achievement of the residual stress reduction process.

[0154] In summary, by performing parameter analysis on the key characteristics of multi-dimensional vibration control parameters to obtain a set of parameter features, the core attributes directly related to residual stress reduction can be extracted from complex control parameters. Irrelevant or redundant parameter information can be eliminated, allowing subsequent analysis to focus on key influencing factors. This avoids low analysis efficiency or deviation due to too many parameter dimensions, laying the foundation for accurately assessing the degree of parameter influence.

[0155] In summary, correlation analysis of parameter feature sets to obtain similar characteristic data can identify the correlation patterns between different control parameter features, clarify the intrinsic relationship between parameters, avoid the one-sidedness of evaluation caused by isolated analysis of a single parameter, and reduce redundant calculations by classifying similar characteristics, thereby improving the efficiency of subsequent comprehensive evaluation.

[0156] In summary, a comprehensive evaluation based on the correspondence between similar characteristic data and standardized evaluation indicators can combine the correlation patterns of parameter characteristics with the quantitative indicators of residual stress reduction effects. Through the mapping analysis of the two, the actual strength of the effect of different parameter combinations or individual parameters on residual stress reduction can be accurately determined, avoiding the bias of relying solely on the properties of the parameters themselves or a single indicator for evaluation. The final parameter influence degree obtained is more in line with actual control needs, providing an accurate basis for the importance of parameters for subsequent multi-objective trade-off analysis.

[0157] S5. Based on the optimized vibration parameters, perform robustness analysis on the vibration control command sequence of the titanium alloy forging to obtain the final control command of the titanium alloy forging.

[0158] In this embodiment of the invention, the robustness analysis of the vibration control command sequence of the titanium alloy forging based on the optimized vibration parameters to obtain the final control command of the titanium alloy forging includes:

[0159] Uncertainty quantification is performed on the optimized vibration parameters to obtain the parameter fluctuation range of the titanium alloy forging;

[0160] Based on the parameter fluctuation range, multi-scenario disturbance simulation is performed on the vibration control command sequence to obtain the command execution deviation dataset of the titanium alloy forging.

[0161] The stability of the instruction execution deviation dataset is evaluated to obtain its stability level.

[0162] Based on the stability level, the vibration control command sequence is adjusted to a fault-tolerant structure to obtain the final control command for the titanium alloy forging.

[0163] Specifically, when quantifying the uncertainty of optimized vibration parameters to obtain the parameter fluctuation range of titanium alloy forgings, the specific content of the optimized vibration parameters is first clarified, including the vibration frequency, vibration amplitude, vibration direction switching time, and total vibration duration. Then, various factors that may cause fluctuations in these parameters are analyzed. For example, instability in the power supply voltage of the vibration equipment may cause a shift in the vibration frequency; minor wear of internal transmission components may cause a deviation in the vibration amplitude; and changes in ambient temperature may affect the response speed of vibration direction switching, thus altering the switching time. For each optimized vibration parameter, combined with its corresponding fluctuation factors, vibration control of similar titanium alloy forgings is referenced. Based on historical experimental data and equipment operation logs, the potential fluctuation range of this parameter in practical applications was determined: for example, the optimized vibration frequency value is 120Hz, and according to the power supply voltage fluctuation record, a voltage change of ±4% will cause a frequency fluctuation of ±4Hz, so the vibration frequency parameter fluctuation range was determined to be 116-124Hz; the optimized vibration amplitude value is 0.4mm, and considering the influence of wear on transmission components, the amplitude may vary between 0.38-0.42mm, so the amplitude parameter fluctuation range was determined accordingly; following the same logic, the fluctuation range of other optimized vibration parameters such as vibration direction switching time and total vibration duration was determined one by one, and the combined results formed the parameter fluctuation range of the titanium alloy forging.

[0164] Furthermore, when performing multi-scenario disturbance simulations on the vibration control command sequence based on the parameter fluctuation range to obtain the command execution deviation dataset, the vibration control command sequence is first decomposed into independent command modules corresponding to each optimized vibration parameter, such as "frequency control command module," "amplitude control command module," "direction switching command module," and "duration control command module." Each module contains the optimized parameter value and the corresponding execution timing requirements. Then, multiple disturbance scenarios are designed based on the parameter fluctuation range. Each scenario corresponds to a set of values ​​for each parameter after fluctuation, ensuring coverage of extreme cases and common combinations of parameter fluctuations. For example, scenario 1 is "vibration frequency takes the lower limit of the fluctuation range, vibration amplitude takes the upper limit of the fluctuation range, and other parameters take the optimized value," and scenario 2 is "vibration frequency takes the upper limit of the fluctuation range, ... Scenario 1 uses the lower limit of the fluctuation range for vibration amplitude and the optimized value for other parameters. Scenario 2 uses the middle value of the fluctuation range for all parameters. Scenario 3 uses the upper limit of the fluctuation range for vibration frequency, the upper limit of the amplitude, the lower limit of the direction switching time, and the upper limit of the total duration. Then, each disturbance scenario is loaded sequentially in the simulated virtual space. The parameter fluctuation values ​​in the scenario are substituted into the corresponding instruction module to generate a vibration control instruction sequence after disturbance and simulate the execution process. At the same time, the deviation between the actual output parameter value and the optimized value of each instruction module in each execution is recorded in real time, as well as the vibration response deviation of the titanium alloy forging caused by the deviation. The deviation data recorded in all scenarios are classified and organized by scenario to form a titanium alloy forging instruction execution deviation dataset containing the deviation of each parameter, the response deviation, and the corresponding scenario information.

[0165] Furthermore, when conducting a stability assessment of the instruction execution deviation dataset to obtain a stability level, the core indicators for stability assessment are first set, including the maximum deviation, the average deviation, and the deviation dispersion. Then, based on the quality standards and industry specifications for residual stress reduction in titanium alloy forgings, the allowable thresholds for each assessment indicator are determined: for example, the allowable threshold for the maximum frequency deviation is ±5Hz, the allowable threshold for the maximum amplitude deviation is ±0.03mm, the allowable thresholds for the average deviation are ±2Hz and ±0.01mm, and the allowable thresholds for deviation dispersion are 6Hz and 0.04mm. Subsequently, the assessment indicators are calculated for each type of deviation data in the instruction execution deviation dataset: for example, the maximum frequency deviation is calculated to be -4Hz in all scenarios. The average value is -1.5Hz and the dispersion is 5Hz, both within the allowable threshold range. The maximum amplitude deviation is +0.02mm, the average value is +0.008mm, and the dispersion is 0.03mm, which also meets the threshold requirements. The various evaluation indicators of displacement response deviation also do not exceed the allowable range. Based on the evaluation results, the stability level is divided. If all evaluation indicators meet the allowable threshold and have a certain safety margin from the threshold, it is judged as "high stability level". If some indicators are close to the threshold but do not exceed it, it is judged as "medium stability level". If there are indicators that exceed the threshold, it is judged as "low stability level". Here, based on the calculation results, it is judged as "high stability level". This level is the stability level of the instruction execution deviation dataset.

[0166] Furthermore, when adjusting the vibration control command sequence according to the stability level to obtain the final control command for the titanium alloy forging, the fault-tolerant adjustment strategy corresponding to different stability levels is first clarified: "High stability level" requires strengthening the command's resistance to small fluctuations to avoid the accumulation of small deviations affecting the stress reduction effect; "Medium stability level" requires adding a deviation compensation mechanism to correct parameter fluctuations in real time; "Low stability level" requires redesigning the command logic to ensure that parameter fluctuations are controllable; based on the previously determined "high stability level", a fault-tolerant adjustment scheme to resist small fluctuations is adopted: for the "frequency control command module", voltage monitoring linkage logic is added to the command. When the power supply voltage fluctuation reaches ±3%, the command automatically triggers the frequency compensation algorithm to adjust the frequency output value according to the voltage fluctuation amplitude to maintain the actual frequency close to the optimized value; for the "vibration control command module", voltage monitoring linkage logic is added to the command. When the power supply voltage fluctuation reaches ±3%, the command automatically triggers the frequency compensation algorithm to adjust the frequency output value according to the voltage fluctuation amplitude to maintain the actual frequency close to the optimized value; for the "vibration control command module", voltage monitoring linkage logic is added to the command. The "Amplitude Control Command Module" adds a wear compensation command for transmission components. Based on the cumulative operating time of the equipment, a preset amplitude compensation coefficient is used, automatically increasing the amplitude compensation value by 0.005mm every 80 hours of operation to offset amplitude deviations caused by component wear. For the "Direction Switching Command Module," a temperature sensing adjustment command is added, correcting the switching response time according to changes in ambient temperature. For every 8°C increase in temperature, the switching response time is shortened by 0.02 seconds to ensure stable direction switching time. These fault-tolerant adjustment logics are embedded into the corresponding modules of the original vibration control command sequence, forming an adjusted vibration control command sequence. Simulation verification confirms that the adjusted commands further reduce the deviation between the actual output values ​​and optimized values ​​of each parameter under parameter fluctuation scenarios, and can stably meet the residual stress reduction requirements. This adjusted command sequence is the final control command for titanium alloy forgings.

[0167] In summary, quantifying the uncertainty of optimized vibration parameters to obtain the parameter fluctuation range can accurately identify the fluctuation range that parameters may occur in actual execution, predict parameter instability factors in advance, avoid deviations in subsequent command execution due to ignoring parameter fluctuations, provide clear variable boundaries for multi-scenario disturbance simulation, and ensure that the analysis covers parameter changes that may occur in actual production.

[0168] In summary, multi-scenario disturbance simulation of vibration control command sequences based on parameter fluctuation ranges can simulate the actual execution state of commands under different parameter fluctuation combinations, generating a comprehensive command execution deviation dataset, rather than relying solely on a single result under ideal parameters. This fully presents the adaptability of commands under complex working conditions, provides rich data support for stability assessment, and avoids robustness analysis loopholes caused by incomplete scenario coverage.

[0169] In summary, by conducting stability assessments and determining the stability level of instruction execution deviation datasets, the anti-interference capability of instruction sequences can be graded and judged by quantifying indicators such as deviation magnitude and deviation frequency. This clarifies the reliability of instruction sequences under different fluctuation scenarios, provides a clear judgment standard for subsequent fault-tolerant adjustments, and avoids blind adjustments caused by experience.

[0170] In summary, adjusting the vibration control command sequence according to the stability level allows for differentiated optimization strategies for different stability levels. This enables the adjusted final control command to have the ability to cope with parameter fluctuations, reduces the decline in residual stress reduction effect caused by parameter deviations during actual execution, ensures the stability and reliability of the control process, and guarantees that the final control command can be implemented and its effect can be guaranteed.

[0171] S6. Based on the final control command, the residual stress reduction effect of the titanium alloy forging is verified in multiple dimensions to obtain the final residual stress reduction report of the titanium alloy forging.

[0172] In this embodiment of the invention, when verifying the residual stress reduction effect of titanium alloy forgings based on the final control command, it is necessary to carry out the verification from multiple dimensions: first, the residual stress values ​​of key parts are detected by the blind hole method, and the compliance status is statistically compared with the preset qualified threshold; then, the stress distribution is judged to meet the uniformity requirements by standard deviation analysis and stress cloud map; at the same time, the structural integrity is confirmed by combining appearance inspection and ultrasonic testing, and the mechanical performance stability is verified by 100-hour environmental simulation test.

[0173] Furthermore, after completing the multi-dimensional verification, the verification methods, test data and judgment results of each dimension are compiled to form the final residual stress reduction report. The report should clearly define the key parameters of the final control command, explain the standard specifications on which the verification is based, and attach supporting materials such as stress cloud diagrams and test images. The report should comprehensively determine whether the reduction effect meets the standard based on the results of each dimension. If there are non-critical dimensions that are close to the threshold, usage precautions should be marked.

[0174] Furthermore, the report fully presents the verification process and conclusions of the residual stress reduction effect based on the final control command. It ensures the comprehensiveness of the verification through multi-dimensional testing and supports the credibility of the conclusions with data and materials, providing a reliable basis for the subsequent application of titanium alloy forgings.

[0175] In summary, multi-dimensional verification of the residual stress reduction effect of titanium alloy forgings can avoid the limitations of single-dimensional verification. The evaluation is carried out from multiple core dimensions such as stress distribution uniformity, stress reduction, and mechanical property stability of forgings, which comprehensively covers the key performance indicators of residual stress reduction and ensures that the verification results can truly reflect the control effect.

[0176] In summary, conducting verification based on the final control command can directly link the control process and its effects, clarify the actual effectiveness of the final control command in reducing residual stress, avoid the disconnect between verification and control, provide a direct basis for subsequent judgment of the effectiveness of the control command, and at the same time, can also reverse verify the rationality of previous parameter optimization, robustness analysis and other steps.

[0177] In summary, the final residual stress reduction report generated through multi-dimensional verification can systematically integrate verification data, effect conclusions, and key parameter information. This provides standardized documentation support for the quality assessment of this batch of titanium alloy forgings and offers a reference process case for residual stress control of similar forgings in the future. It also helps to optimize and iterate subsequent control schemes and improves the standardization and efficiency of overall residual stress reduction control.

[0178] like Figure 2 The diagram shown is a functional block diagram of a residual stress reduction control system for titanium alloy forgings provided in an embodiment of the present invention.

[0179] The residual stress reduction control system 100 for titanium alloy forgings described in this invention can be installed in an electronic device. Depending on the functions implemented, the residual stress reduction control system 100 may include a vibration parameter adjustment module 101, a dynamic response vibration module 102, a residual stress assessment module 103, a vibration parameter optimization module 104, an optimized control command module 105, and a residual stress verification module 106. The modules described in this invention can also be referred to as units, which are a series of computer program segments that can be executed by the processor of an electronic device and perform a fixed function, and are stored in the memory of the electronic device.

[0180] In this embodiment, the functions of each module / unit are as follows:

[0181] The vibration parameter control module 101 is used to perform multi-physics field coupled vibration control on the titanium alloy forging based on the initial state data of the titanium alloy forging, so as to obtain the multi-dimensional vibration control parameters of the titanium alloy forging.

[0182] The dynamic response vibration module 102 is used to apply multi-directional vibration to the titanium alloy forging based on the multi-dimensional vibration control parameters to obtain the dynamic response data of the titanium alloy forging.

[0183] The residual stress assessment module 103 is used to perform multimodal data fusion on the dynamic response data to obtain the residual stress reduction assessment index of the titanium alloy forging.

[0184] The vibration parameter optimization module 104 is used to make multi-objective decisions on the multi-dimensional vibration control parameters based on the residual stress reduction evaluation index, so as to obtain the optimized vibration parameters of the titanium alloy forging.

[0185] The optimized control command module 105 is used to perform robustness analysis on the vibration control command sequence of the titanium alloy forging based on the optimized vibration parameters, and obtain the final control command of the titanium alloy forging.

[0186] The residual stress verification module 106 is used to perform multi-dimensional verification of the residual stress reduction effect of the titanium alloy forging based on the final control command, and obtain the final residual stress reduction report of the titanium alloy forging.

[0187] In the several embodiments provided by this invention, it should be understood that the disclosed methods and systems can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0188] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0189] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0190] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0191] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0192] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for controlling residual stress reduction in titanium alloy forgings, characterized in that, The method includes: S1. Based on the initial state data of the titanium alloy forging, multi-physics field coupled vibration control is performed on the titanium alloy forging to obtain multi-dimensional vibration control parameters of the titanium alloy forging, including: Feature extraction is performed on the historical process data in the initial state data to obtain the process influence factor of the titanium alloy forging; By coupling the geometric configuration data, material property data, and process influence factors in the initial state data, the comprehensive state data of the titanium alloy forging is obtained. The initial control parameters of the titanium alloy forging are obtained by performing multiphysics field constraint optimization on the comprehensive state data. The initial control parameters are checked for coordination to obtain the multi-dimensional vibration control parameters of the titanium alloy forging. S2. Based on the multi-dimensional vibration control parameters, apply multi-directional vibration to the titanium alloy forging to obtain the dynamic response data of the titanium alloy forging; S3. Perform multimodal data fusion on the dynamic response data to obtain the residual stress reduction evaluation index of the titanium alloy forging, including: The dynamic response data is subjected to signal integrity verification to obtain the verified dynamic response data of the titanium alloy forging. Empirical mode decomposition is performed on the verified dynamic response data to obtain the intrinsic mode components of the titanium alloy forging. Based on the sample entropy of the intrinsic mode components, construct the weighted fusion matrix of the intrinsic mode components; Based on the weighted fusion matrix, the residual stress reduction assessment index is calculated, wherein the calculation formula for the residual stress reduction assessment index is: ; in, This represents the residual stress reduction assessment index. This represents the total number of the intrinsic modal components. Indicates the first The weights of the intrinsic mode components. This represents the total number of data points for each of the intrinsic mode components. Indicates the first The intrinsic mode components are at time... Quantity, Indicates the first The average value of each of the intrinsic modal components; S4. Based on the residual stress reduction evaluation index, perform multi-objective decision-making on the multi-dimensional vibration control parameters to obtain the optimized vibration parameters of the titanium alloy forging. S5. Based on the optimized vibration parameters, perform robustness analysis on the vibration control command sequence of the titanium alloy forging to obtain the final control command of the titanium alloy forging. S6. Based on the final control command, the residual stress reduction effect of the titanium alloy forging is verified in multiple dimensions to obtain the final residual stress reduction report of the titanium alloy forging.

2. The method for reducing and controlling residual stress in titanium alloy forgings as described in claim 1, characterized in that, The process of applying multi-directional vibration to the titanium alloy forging based on the multi-dimensional vibration control parameters to obtain dynamic response data of the titanium alloy forging includes: Modal decoupling is performed on the multi-dimensional vibration control parameters to obtain the independent vibration command sequence of the titanium alloy forging; Based on the response acquisition channel of the simulated virtual space, multi-directional vibration is applied to the titanium alloy forging to obtain the primary response flow of the titanium alloy forging; Time-frequency domain analysis was performed on the primary response flow to obtain various dynamic indicators of the titanium alloy forging. The dynamic response data of the titanium alloy forging is obtained by aligning the various dynamic indicators with timestamps.

3. The method for reducing and controlling residual stress in titanium alloy forgings as described in claim 2, characterized in that, The response acquisition channel based on simulated virtual space applies multi-directional vibration to the titanium alloy forging to obtain the primary response flow of the titanium alloy forging, including: Based on the geometric configuration data in the initial state data, virtual measuring points are defined on the titanium alloy forging. Based on the virtual measuring points, construct a response data acquisition network connecting the virtual measuring points; Based on the response data acquisition network, the independent vibration command sequence is applied to the titanium alloy forging to obtain the original response signal of the titanium alloy forging; The original response signal is subjected to integrity verification to obtain the primary response flow of the titanium alloy forging.

4. The method for reducing and controlling residual stress in titanium alloy forgings as described in claim 1, characterized in that, The step of constructing the weighted fusion matrix of the intrinsic mode components based on the sample entropy of the intrinsic mode components includes: Based on a preset weight range, the sample entropy is reconstructed to obtain the initial weights of the titanium alloy forging. The initial weights are normalized to obtain the final weights of the titanium alloy forgings. The final weights are assigned to the intrinsic mode components according to the corresponding relationship to form a weighted fusion matrix of the intrinsic mode components.

5. The method for reducing and controlling residual stress in titanium alloy forgings as described in claim 1, characterized in that, The optimized vibration parameters of the titanium alloy forging are obtained by performing multi-objective decision-making on the multi-dimensional vibration control parameters based on the residual stress reduction evaluation index, including: The residual stress reduction evaluation index is standardized in multiple dimensions to obtain the standardized evaluation index of the titanium alloy forging. Based on the standardized evaluation index, the multi-dimensional vibration control parameters are prioritized to obtain the degree of influence of the multi-dimensional vibration control parameters on the reduction of residual stress in the titanium alloy forging. Based on the degree of influence, a multi-objective trade-off analysis is performed on the multi-dimensional vibration control parameters to obtain the preliminary optimized parameters of the titanium alloy forging. The initial optimized parameters were verified for consistency to obtain the optimized vibration parameters of the titanium alloy forging.

6. The method for reducing and controlling residual stress in titanium alloy forgings as described in claim 5, characterized in that, Based on the standardized evaluation indicators, the multi-dimensional vibration control parameters are prioritized to obtain the degree of influence of the multi-dimensional vibration control parameters on the reduction of residual stress in the titanium alloy forging, including: The key features in the multi-dimensional vibration control parameters are analyzed to obtain the parameter feature set of the multi-dimensional vibration control parameters; Correlation analysis is performed on the parameter feature set to obtain similarity characteristic data of the multi-dimensional vibration control parameters; Based on the correspondence between the similarity characteristic data and the standardized evaluation indicators, the multi-dimensional vibration control parameters are comprehensively evaluated to obtain the degree of influence of the multi-dimensional vibration control parameters on the reduction of residual stress in the titanium alloy forging.

7. The method for reducing and controlling residual stress in titanium alloy forgings as described in claim 1, characterized in that, Based on the optimized vibration parameters, a robustness analysis is performed on the vibration control command sequence of the titanium alloy forging to obtain the final control command for the titanium alloy forging, including: Uncertainty quantification is performed on the optimized vibration parameters to obtain the parameter fluctuation range of the titanium alloy forging; Based on the parameter fluctuation range, multi-scenario disturbance simulation is performed on the vibration control command sequence to obtain the command execution deviation dataset of the titanium alloy forging. The stability of the instruction execution deviation dataset is evaluated to obtain its stability level. Based on the stability level, the vibration control command sequence is adjusted to a fault-tolerant structure to obtain the final control command for the titanium alloy forging.

8. A residual stress reduction control system for titanium alloy forgings, characterized in that, The system includes: The vibration parameter control module is used to perform multi-physics field coupled vibration control on the titanium alloy forging based on the initial state data of the titanium alloy forging, and to obtain multi-dimensional vibration control parameters of the titanium alloy forging, including: Feature extraction is performed on the historical process data in the initial state data to obtain the process influence factor of the titanium alloy forging; By coupling the geometric configuration data, material property data, and process influence factors in the initial state data, the comprehensive state data of the titanium alloy forging is obtained. The initial control parameters of the titanium alloy forging are obtained by performing multiphysics field constraint optimization on the comprehensive state data. The initial control parameters are checked for coordination to obtain the multi-dimensional vibration control parameters of the titanium alloy forging. A dynamic response vibration module is used to apply multi-directional vibration to the titanium alloy forging based on the multi-dimensional vibration control parameters to obtain the dynamic response data of the titanium alloy forging. The residual stress assessment module is used to perform multimodal data fusion on the dynamic response data to obtain the residual stress reduction assessment index of the titanium alloy forging, including: The dynamic response data is subjected to signal integrity verification to obtain the verified dynamic response data of the titanium alloy forging. Empirical mode decomposition is performed on the verified dynamic response data to obtain the intrinsic mode components of the titanium alloy forging. Based on the sample entropy of the intrinsic mode components, construct the weighted fusion matrix of the intrinsic mode components; Based on the weighted fusion matrix, the residual stress reduction assessment index is calculated, wherein the calculation formula for the residual stress reduction assessment index is: ; in, This represents the residual stress reduction assessment index. This represents the total number of the intrinsic modal components. Indicates the first The weights of the intrinsic mode components. This represents the total number of data points for each of the intrinsic mode components. Indicates the first The intrinsic mode components are at time... Quantity, Indicates the first The average value of each of the intrinsic modal components; The vibration parameter optimization module is used to make multi-objective decisions on the multi-dimensional vibration control parameters based on the residual stress reduction evaluation index, so as to obtain the optimized vibration parameters of the titanium alloy forging. An optimized control command module is used to perform robustness analysis on the vibration control command sequence of the titanium alloy forging based on the optimized vibration parameters, and to obtain the final control command of the titanium alloy forging. The residual stress verification module is used to perform multi-dimensional verification of the residual stress reduction effect of the titanium alloy forging based on the final control command, and obtain the final residual stress reduction report of the titanium alloy forging.

Images