Micro spring washer efficient forming method applying ant colony algorithm

By combining ant colony algorithm, quantum superphase search technology and self-organizing critical optimization technology, the global optimization of the micro spring washer molding process and the stability of the production process are achieved, and the shortcomings of process parameter optimization and production process control in traditional technologies are solved, and the molding accuracy and production efficiency are significantly improved.

CN120124209APending Publication Date: 2025-06-10DONGTAI JIANGLONG METAL MFG CO LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202510189866.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-02-20
Publication Date
2025-06-10

AI Technical Summary

Technical Problem

The existing micro spring washer molding technology has shortcomings in process parameter optimization and production process control, and it is difficult to meet the requirements of efficient production and high quality.

Method used

Ant colony algorithm, quantum superphase search technology and self-organizing critical optimization technology are used to achieve global optimal solution of process parameters and stability of production process processes through multi-dimensional solution space optimization, real-time feedback mechanism and dynamic adjustment of process parameters.

Benefits of technology

It significantly improves molding accuracy, production efficiency and material utilization, ensures the stability and consistency of the production process, and reduces production costs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120124209A_ABST
    Figure CN120124209A_ABST
Patent Text Reader

Abstract

The invention discloses a miniature spring washer efficient forming method applying an ant colony algorithm, and the method comprises the following steps: S1, setting an initial process parameter range according to miniature spring washer forming requirements; s2, constructing an ant colony optimization model based on a set parameter range; s3, adopting a space-time ripple propagation algorithm to screen out a preliminarily optimized process parameter combination; s4, based on the screened parameter combination, a super-dimension interference optimization technology is adopted, and a search path is adjusted; s5, further optimizing the parameter combination by using a quantum super-phase search technology; s6, further approaching a global optimal solution through a self-organizing critical optimization technology; s7, performing real-time monitoring and dynamic adjustment by adopting a space-time coupling feedback mechanism; and S8, in the actual production process, a reverse feedback simulation mechanism is applied, and the subsequent production process is optimized and improved. The production efficiency, the forming precision and the material utilization rate of the miniature spring washer can be effectively improved, and the stability and the consistency of the production process are ensured.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of manufacturing process optimization, and particularly to an efficient forming method for micro spring washers applying the ant colony algorithm. Background Art

[0002] With the continuous development of the manufacturing industry, the demand for micro parts is increasing day by day. Among them, as one of the key mechanical components, micro spring washers play a crucial role in fields such as precision machinery and electronic devices. However, due to their small size and complex shape, how to improve their production efficiency, forming accuracy, and material utilization rate has always been a major challenge faced by the industry. The existing forming technologies for micro spring washers have many deficiencies in the optimization of process parameters and the control of the production process, and it is difficult to meet the requirements of high-efficiency production and high quality.

[0003] Most traditional forming methods for micro spring washers rely on empirical adjustment of process parameters and adopt methods based on single-objective optimization to adjust the forming process. Specifically, these methods mainly have the following defects:

[0004] 1. The setting of process parameters depends on experience and lacks a systematic optimization mechanism: In traditional forming processes, the setting of process parameters often depends on the experience of operators. This method is difficult to ensure the optimality and consistency of parameters, resulting in the forming accuracy and production efficiency not reaching the expected level. At the same time, existing methods usually ignore the mutual influence between different process parameters and cannot systematically optimize multiple parameters to improve the overall forming effect.

[0005] 2. Lack of a multi-objective optimization mechanism and it is difficult to balance multiple production requirements: Traditional methods usually only adjust for a single optimization objective, such as only focusing on forming accuracy or production efficiency, but cannot find a balance among forming accuracy, production efficiency, and material utilization rate. Therefore, in actual production, the situation of sacrificing other indicators to improve a certain indicator often occurs, resulting in the limitation of the improvement of the overall process level.

[0006] 3. The adjustment of process parameters is not flexible enough and lacks a real-time monitoring and feedback mechanism: The adjustment of existing forming process parameters is usually static and it is difficult to respond in a timely manner to changes in process conditions during the production process. Once the production environment changes, such as fluctuations in material properties or external environmental conditions, traditional methods often cannot quickly adjust the process parameters to adapt to the new conditions, resulting in unstable forming quality and an increase in the scrap rate. In addition, traditional methods lack a real-time monitoring and feedback mechanism and cannot immediately correct and optimize the deviations during the production process.

[0007] 4. Single algorithms and technical means, making it difficult to fully utilize emerging technologies: Most traditional forming processes rely on simple optimization algorithms or empirical rules and fail to fully utilize emerging technologies such as ant colony algorithms and quantum algorithms. These technologies have great potential in solving complex problems, but their applications in the forming process of micro-parts are not yet mature. Existing technologies are difficult to handle multi-dimensional and multi-objective optimization problems and cannot maintain the optimality of process parameters in a dynamically changing production environment.

[0008] 5. Insufficient ability to search complex solution spaces and prone to falling into local optimal solutions: In traditional optimization methods, due to limited algorithm capabilities, it is often difficult to find the global optimal solution in complex solution spaces and is prone to falling into local optimal solutions, resulting in unsatisfactory optimization effects of process parameters. This problem is particularly prominent in multi-dimensional parameter optimization, and existing methods cannot effectively handle the complex interaction relationships between process parameters.

[0009] Therefore, how to provide an efficient forming method for micro spring washers applying ant colony algorithms is an urgent problem to be solved by those skilled in the art. Summary of the Invention

[0010] An object of the present invention is to propose an efficient forming method for micro spring washers applying ant colony algorithms. The present invention fully utilizes ant colony algorithms, quantum superposition search technology, and self-organized critical optimization technology, and details the dynamic adjustment and optimization of process parameters through the optimization of multi-dimensional solution spaces and the application of real-time feedback mechanisms, with the advantages of high forming accuracy, high production efficiency, high material utilization rate, and production process stability.

[0011] An efficient forming method for micro spring washers applying ant colony algorithms according to an embodiment of the present invention includes the following steps:

[0012] S1. According to the forming requirements of micro spring washers, set the initial process parameter range, determine the optimization objectives, including forming accuracy, production efficiency, and material utilization rate, and clarify the weight coefficients of each objective;

[0013] S2. Based on the set parameter range, construct an ant colony optimization model, initialize the ant colony, set the path selection probability, pheromone update rule, heuristic factor, and pheromone evaporation coefficient, and generate an initial solution space;

[0014] S3. Adopt the space-time ripple propagation algorithm, simulate the ripple propagation effect in the solution space, and guide the ant colony to preferentially explore high-potential areas according to the intensity and propagation path of the ripples, so as to screen out a preliminarily optimized combination of process parameters;

[0015] S4. Based on the initially screened parameter combinations, use the hyper-dimensional interference optimization technique to expand the solution space to multiple dimensions, enabling the ant colony to explore potential global optimal solutions in the multi-dimensional space and adaptively adjust the search path;

[0016] S5. In the expanded multi-dimensional solution space, combine the quantum super-phase search technique, regard the process parameter combination as a quantum state, and through the superposition, interference, and entanglement effects of the quantum state, search for multiple potential optimization paths in parallel to further optimize the process parameter combination;

[0017] S6. As the quantum super-phase search technique converges, through the self-organized critical optimization technique, when the system is in the critical state, further approximate the global optimal solution by adaptively adjusting the process parameter combination;

[0018] S7. Apply the obtained optimal process parameter combination to the actual production process, adopt a spatio-temporal coupling feedback mechanism, combine the data in the time and space dimensions during the production process, and conduct real-time monitoring and dynamic adjustment of the process parameter changes during the forming process;

[0019] S8. In the actual production process, apply the reverse feedback simulation mechanism to analyze the deviations that occur during the production process, and pre-adjust the process parameters in the virtual environment to optimize and improve the subsequent production process.

[0020] Optionally, S3 includes the following steps:

[0021] S31. By establishing a multi-dimensional model of the solution space, use the spatio-temporal ripple propagation algorithm to initialize the solution space and generate an initial ripple. The intensity of the initial ripple is determined according to the initial fitness value of the process parameter combination;

[0022] S32. Based on the intensity of the initial ripple, apply a multi-level ripple propagation model to conduct a coarse-grained first-layer ripple propagation. By simulating the propagation of the ripple in the solution space, generate a first-layer ripple diagram and determine a preliminary excellent process parameter region;

[0023] S33. Generate a second-layer ripple within the determined preliminary excellent region and conduct a finer-grained search through the second-layer ripple propagation:

[0024]

[0025] where, I 2 (x, t) represents the intensity of the second-layer ripple within the excellent region, I 1 (x, t) is the intensity of the first-layer ripple, and α, β, γ, θ, δ are non-linear dynamic parameters for adjusting the ripple intensity, used to control the non-linear characteristics of the ripple propagation, is the gradient modulus of the first-layer ripple intensity, used to represent the change rate of the ripple intensity, represents the second derivative of the first-layer ripple intensity with respect to time;

[0026] S34. According to the intensity distribution of the second-layer ripples, guide the ant colony to preferentially explore the high-potential areas with higher intensities, and select the optimal search route in the solution space according to the ripple propagation path and intensity change, so as to gradually optimize the process parameter combination;

[0027] S35. Through the layer-by-layer refinement of the multi-level ripple propagation model and the collaborative search of the ant colony, finally screen out the preliminarily optimized process parameter combination, which will be used as the basis for further optimization in the subsequent steps.

[0028] Optionally, the S4 includes the following steps:

[0029] S41. On the basis of the preliminarily screened parameter combination, construct an extended solution space model, and form a multi-dimensional solution space by adding additional dimensions, so that the ant colony can search in a wider and more complex space;

[0030] S42. In the multi-dimensional solution space, initialize the search paths of the ant colony, and adjust the initial direction and step size of each path according to the initial conditions on each dimension, so that the ants can explore in a more promising direction at the initial stage of the search;

[0031] S43. In the multi-dimensional solution space, adopt the hyper-dimensional interference optimization technology for the adjusted initialization paths, dynamically adjust the search paths of the ant colony, and combine the spontaneous symmetry breaking mechanism to obtain more search directions:

[0032]

[0033] where P t+1 is the position of the path at the (t + 1)-th step, P t is the position of the path at the t-th step, η and ζ are the adjustment parameters for path update, I 2 (x, t) is the second-layer ripple propagation intensity, which is an important factor for path selection, M t is the interference matrix of the path, representing the comprehensive intensity of multi-dimensional interaction effects, which affects the global direction of path selection, W t is the weight matrix, reflecting the importance of each dimension, and weighting according to the contribution of different dimensions to path update, is the gradient of the fitness function, used to indicate the best optimization direction of the current path, D t is the path adjustment direction matrix, used to further correct the path, ξ is the adjustment factor of the spontaneous symmetry breaking mechanism, used to control the intensity of the perturbation, ΔS tIt is the perturbation vector caused by spontaneous symmetry breaking, which breaks the symmetry of the path through perturbation and guides the path into more diverse search directions;

[0034] S44. At each step of updating the search path, dynamically calculate the interference matrix M on the path t , by combining the path optimization guided by spontaneous symmetry breaking, enabling the ant colony to break symmetry in the solution space and explore more potential optimal solution regions;

[0035] S45. Through the optimized search of the path in the multi-dimensional solution space and the path correction guided by spontaneous symmetry breaking, adaptively adjust the search path.

[0036] Optionally, the S6 includes the following steps:

[0037] S61. During the process of the quantum super-phase search technology gradually converging, utilize the self-organized critical optimization technology to make the system enter the critical state, and automatically adjust the position of the critical point according to the real-time changes of the process parameters to adapt to different production conditions and requirements;

[0038] S62. Introduce a critical point dynamic adjustment mechanism. By real-time monitoring the changes in the combination of production data and process parameters, the system can identify the distance between the current state and the initial critical point λ c and dynamically adjust the position of the critical point:

[0039]

[0040] where, λ c (t + 1) is the position of the dynamically adjusted critical point at the (t + 1)-th moment, λ c (t) is the position of the critical point at the t-th moment, α(t) is the adjustment factor at time t, used to control the dynamic adjustment amplitude of the critical point, is the system state gradient of the current process parameter combination, β(t) is the feedback adjustment coefficient at time t, I 2 (x, t) is the generated second-layer ripple propagation intensity, which is an important factor affecting the critical point adjustment, and F(λ(t)) is the correction function of the feedback control system, used to further optimize the process parameter combination;

[0041] S63. During the dynamic adjustment of the critical point, the system continuously corrects and optimizes the process parameters through adaptive adjustment according to the state of the real-time production data and the process parameter combination;

[0042] S64. After each adjustment, the system analyzes the influence of the new critical point λ c (t + 1) on the process parameter combination, evaluates the system state in real time and updates the optimization path, gradually approaching the global optimal solution.

[0043] Optionally, S7 includes the following steps:

[0044] S71. Apply the obtained optimal process parameter combination to the actual production process and establish a spatio-temporal coupling feedback mechanism model;

[0045] S72. Introduce a multi-level collaborative ant colony algorithm into the spatio-temporal coupling feedback mechanism. By dividing the optimization task of the process parameter combination λ(t,X) into multiple levels, each level corresponds to different production goals;

[0046] S73. At each level of the multi-level collaborative ant colony algorithm, collect the process parameter data related to time t and spatial position X in real time during the production process, and input these data into the feedback control system:

[0047]

[0048] where λ(t + 1,X) is the process parameter combination at the (t + 1)-th moment and spatial position X, γ(t) is the spatio-temporal coupling feedback control factor, is the gradient of the system state function with respect to the process parameter combination, δ(t) is the feedback adjustment coefficient in the time dimension, is the change rate of the process parameter combination with respect to time, and ξ(t) is the adjustment factor;

[0049] S74. During the production process, use the multi-level collaborative ant colony algorithm to adjust the state of the process parameter combination in real time. When the system detects that the process parameter combination deviates from the optimal state, the ant colonies at each level work together and are corrected through the feedback control system to make the parameter combination return to the optimal path;

[0050] S75. Combine the operation data of the production equipment to dynamically optimize the system state function S(λ(t,X)), and through the dynamic adjustment of the critical point, make the process parameter combination maintain the optimal state in the dynamic production environment.

[0051] Optionally, S8 includes the following steps:

[0052] S81. In the actual production process, apply a multi-level reverse feedback simulation mechanism, divide the process parameter deviations that occur during the production process into short-term deviations and long-term deviations, establish short-term feedback loops and long-term feedback loops respectively, and adjust according to the process parameter optimization requirements on different time scales;

[0053] S82. In the short-term feedback loop, collect the process parameter data related to time and spatial position in real time during the production process, and calculate the immediate process parameter deviation Δλ s (t,X):

[0054]

[0055] Among them, λ new (t + 1, X) is the process parameter combination at the (t + 1)-th moment and spatial position X after adjustment, κ s (t) is the short-term feedback adjustment factor, γ(t) is the short-term feedback control factor, and ζ(t) is the short-term optimization adjustment factor;

[0056] S83. In the long-term feedback loop, the system combines historical production data and the current process parameter status to perform trend analysis and optimization on the process parameters throughout the production cycle:

[0057]

[0058] Among them, λ opt (t + 1, X) is the process parameter combination after long-term feedback optimization, κ l (t) is the long-term feedback adjustment factor, and P t+1 are the system response gradient and path update result, β(t) is the feedback adjustment coefficient, and F(λ(t, X)) is the feedback correction function;

[0059] S84. Through the multi-level feedback loop, the system can simultaneously perform short-term and long-term process parameter adjustments during the production process. The short-term feedback is used to correct the immediate deviation in production in real time, while the long-term feedback is optimized throughout the production cycle to optimize the overall quality and production efficiency of the product;

[0060] S85. Apply the process parameter combinations optimized by short-term and long-term feedback to the actual production process, continuously monitor the production data, and maintain the process parameters in the optimal state through a dynamic multi-level feedback mechanism.

[0061] The beneficial effects of the present invention are:

[0062] (1) By combining the ant colony algorithm, spatio-temporal ripple propagation technology, and hyperdimensional interference optimization technology, the present invention significantly improves the parameter optimization efficiency and accuracy of the micro spring washer forming process. Especially in terms of global optimization and exploration of complex parameter combinations, the present invention overcomes the deficiency of relying on empirical parameter setting in traditional methods and can effectively find the global optimal solution in the multi-dimensional solution space to ensure the improvement of forming accuracy.

[0063] (2) By introducing quantum superposition phase search technology and self-organized critical optimization technology, the present invention realizes the dynamic adaptive adjustment of process parameters, enhances the adaptability and stability of process parameters under different production conditions. Especially in terms of real-time adjustment and optimization during the production process, the present invention improves the response speed of the system to ensure the stability and consistency of production.

[0064] (3) By combining the spatio-temporal coupling feedback mechanism and the reverse feedback simulation mechanism, the present invention significantly improves the real-time monitoring and adjustment ability of process parameters during the production process. Especially when dealing with parameter deviations during the production process, the present invention can make dynamic adjustments in a timely manner, optimize the subsequent production process, thereby effectively improving the production efficiency and material utilization rate, and achieving a reduction in production costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] The drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation to the present invention. In the drawings:

[0066] Figure 1 is a flowchart of an efficient forming method for micro spring washers applying the ant colony algorithm proposed by the present invention;

[0067] Figure 2 is a schematic diagram of the preliminary process parameter optimization based on the spatio-temporal ripple propagation algorithm proposed by the present invention;

[0068] Figure 3 is a schematic diagram of the quantum state evolution of the quantum superposition phase search technology in the process parameter optimization proposed by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0069] Now, the present invention will be further described in detail with reference to the accompanying drawings. These drawings are all simplified schematic diagrams, only showing the basic structure of the present invention in a schematic way, so they only show the components related to the present invention.

[0070] Referring to Figures 1-3 , an efficient forming method for micro spring washers applying the ant colony algorithm includes the following steps: S1. According to the forming requirements of micro spring washers, set the initial process parameter range, determine the optimization objectives, including forming accuracy, production efficiency and material utilization rate, and clarify the weight coefficients of each objective;

[0071] S2. Based on the set parameter range, construct an ant colony optimization model, initialize the ant colony, set the path selection probability, pheromone update rule, heuristic factor and pheromone evaporation coefficient, and generate an initial solution space;

[0072] S3. Adopt the spatio-temporal ripple propagation algorithm, by simulating the ripple propagation effect in the solution space, guide the ant colony to preferentially explore high-potential areas according to the intensity and propagation path of the ripple, so as to screen out a preliminary optimized process parameter combination;

[0073] S4. Based on the preliminary screened parameter combination, adopt the hyper-dimensional interference optimization technology to expand the solution space to multiple dimensions, enable the ant colony to explore potential global optimal solutions in the multi-dimensional space, and make adaptive adjustments to the search path;

[0074] S5. In the extended multi-dimensional solution space, combining quantum super-phase search technology, regarding the process parameter combination as a quantum state, through the superposition, interference and entanglement effects of quantum states, parallelly search for multiple potential optimization paths to further optimize the process parameter combination;

[0075] S6. As the quantum super-phase search technology converges, through self-organized critical optimization technology, when the system is in the critical state, further approximate the global optimal solution by adaptively adjusting the process parameter combination;

[0076] S7. Apply the obtained optimal process parameter combination to the actual production process, adopt a spatio-temporal coupling feedback mechanism, combine the data in the time and space dimensions during the production process, and conduct real-time monitoring and dynamic adjustment of the changes in process parameters during the forming process;

[0077] S8. In the actual production process, apply the reverse feedback simulation mechanism to analyze the deviations that occur during the production process, and pre-adjust the process parameters in the virtual environment to optimize and improve the subsequent production process.

[0078] In this embodiment, S3 includes the following steps:

[0079] S31. By establishing a multi-dimensional model of the solution space, use the spatio-temporal ripple propagation algorithm to initialize the solution space and generate an initial ripple. The intensity of the initial ripple is determined according to the initial fitness value of the process parameter combination;

[0080] S32. Based on the intensity of the initial ripple, apply a multi-level ripple propagation model to conduct the first-layer coarse-grained ripple propagation. By simulating the propagation of the ripple in the solution space, generate the first-layer ripple diagram and determine the preliminary excellent process parameter region;

[0081] S33. Generate the second-layer ripple within the determined preliminary excellent region, and conduct a finer-grained search through the second-layer ripple propagation:

[0082]

[0083] where, I 2 (x,t) represents the intensity of the second-layer ripple within the excellent region, I 1 (x,t) is the intensity of the first-layer ripple, α, β, γ, θ, δ are non-linear dynamic parameters for adjusting the ripple intensity, used to control the non-linear characteristics of the ripple propagation, is the gradient modulus of the first-layer ripple intensity, used to represent the change rate of the ripple intensity, represents the second-order derivative of the first-layer ripple intensity with respect to time;

[0084] S34. According to the intensity distribution of the second-layer ripples, guide the ant colony to preferentially explore high-potential areas with higher intensities, and select the best search route in the solution space according to the ripple propagation path and intensity changes, so as to gradually optimize the process parameter combination;

[0085] S35. Through the layer-by-layer refinement of the multi-level ripple propagation model and the collaborative search of the ant colony, finally screen out the preliminarily optimized process parameter combination, which will be used as the basis for further optimization in the subsequent steps.

[0086] In this embodiment, the said S4 includes the following steps:

[0087] S41. On the basis of the preliminarily screened parameter combination, construct an extended solution space model. By adding additional dimensions, form a multi-dimensional solution space, enabling the ant colony to search in a wider and more complex space;

[0088] S42. In the multi-dimensional solution space, initialize the search paths of the ant colony. The initial direction and step size of each path are adjusted according to the initial conditions in each dimension, enabling the ants to explore in a more promising direction at the initial stage of the search;

[0089] S43. In the multi-dimensional solution space, adopt the hyper-dimensional interference optimization technique for the adjusted initialized paths, dynamically adjust the search paths of the ant colony, and combine the spontaneous symmetry breaking mechanism to obtain more search directions:

[0090]

[0091] Among them, P t+1 is the position of the path at the (t + 1)-th step, P t is the position of the path at the t-th step, η and ζ are the adjustment parameters for path update, I 2 (x, t) is the second-layer ripple propagation intensity, which is an important factor for path selection, M t is the interference matrix of the path, representing the comprehensive intensity of multi-dimensional interaction effects, which affects the global direction of path selection, W t is the weight matrix, reflecting the importance of each dimension, and weighting according to the contribution of different dimensions to path update, is the gradient of the fitness function, used to indicate the best optimization direction of the current path, D t is the path adjustment direction matrix, used to further correct the path, ξ is the adjustment factor of the spontaneous symmetry breaking mechanism, used to control the intensity of the perturbation, ΔS t is the perturbation vector caused by spontaneous symmetry breaking, breaking the symmetry of the path through perturbation and guiding the path into more diverse search directions;

[0092] S44. At each step of the search path update, dynamically calculate the interference matrix M on the path t , by combining the path optimization guided by spontaneous symmetry breaking, enabling the ant colony to break symmetry in the solution space and explore more potential optimal solution regions;

[0093] S45. Through the optimized search of paths in the multi-dimensional solution space and the path correction guided by spontaneous symmetry breaking, adaptively adjust the search path.

[0094] In this embodiment, the S6 includes the following steps:

[0095] S61. During the process of the quantum superposition search technology gradually converging, utilize the self-organized critical optimization technology to make the system enter the critical state, and automatically adjust the position of the critical point according to the real-time changes of process parameters to adapt to different production conditions and requirements;

[0096] S62. Introduce a critical point dynamic adjustment mechanism. By monitoring the changes in the combination of production data and process parameters in real time, the system can identify the distance between the current state and the initial critical point λ c and dynamically adjust the position of the critical point:

[0097]

[0098] where λ c (t + 1) is the position of the dynamically adjusted critical point at the (t + 1)-th moment, λ c (t) is the position of the critical point at the t-th moment, α(t) is the adjustment factor at time t, used to control the dynamic adjustment amplitude of the critical point, is the system state gradient of the current process parameter combination, β(t) is the feedback adjustment coefficient at time t, I 2 (x, t) is the generated second-layer ripple propagation intensity, which is an important factor affecting the critical point adjustment, and F(λ(t)) is the correction function of the feedback control system, used to further optimize the process parameter combination;

[0099] S63. During the dynamic adjustment of the critical point, the system continuously corrects and optimizes the process parameters through adaptive adjustment according to the state of the real-time production data and the process parameter combination.

[0100] S64. After each adjustment, the system analyzes the influence of the new critical point λ c (t + 1) on the process parameter combination, evaluates the system state in real time and updates the optimization path, gradually approaching the global optimal solution.

[0101] In this embodiment, the S7 includes the following steps:

[0102] S71. Apply the obtained optimal process parameter combination to the actual production process and establish a spatio-temporal coupling feedback mechanism model;

[0103] S72. Introduce a multi-level collaborative ant colony algorithm into the spatio-temporal coupling feedback mechanism. By dividing the optimization task of the process parameter combination λ(t,X) into multiple levels, each level corresponds to different production goals;

[0104] S73. At each level of the multi-level collaborative ant colony algorithm, collect the process parameter data related to time t and spatial position X in real time during the production process and input these data into the feedback control system:

[0105]

[0106] where λ(t + 1,X) is the process parameter combination at the (t + 1)-th moment and spatial position X, γ(t) is the spatio-temporal coupling feedback control factor, is the gradient of the system state function with respect to the process parameter combination, δ(t) is the feedback adjustment coefficient in the time dimension, is the change rate of the process parameter combination with respect to time, and ξ(t) is the adjustment factor;

[0107] S74. During the production process, use the multi-level collaborative ant colony algorithm to adjust the state of the process parameter combination in real time. When the system detects that the process parameter combination deviates from the optimal state, the ant colonies at each layer work together and are corrected through the feedback control system to make the parameter combination return to the optimal path;

[0108] S75. Combine the operation data of the production equipment to dynamically optimize the system state function S(λ(t,X)), and through the dynamic adjustment of the critical points, make the process parameter combination maintain the optimal state in the dynamic production environment.

[0109] In this embodiment, the S8 includes the following steps:

[0110] S81. In the actual production process, apply a multi-level reverse feedback simulation mechanism, divide the process parameter deviations that occur during the production process into short-term deviations and long-term deviations, establish short-term feedback loops and long-term feedback loops respectively, and adjust according to the process parameter optimization requirements of different time scales;

[0111] S82. In the short-term feedback loop, collect the process parameter data related to time and spatial position in real time during the production process and calculate the immediate process parameter deviation Δλ s (t,X):

[0112]

[0113] where λ new(t + 1, X) is the combination of process parameters at the adjusted time t + 1 and spatial position X, κ s (t) is the short-term feedback adjustment factor, γ(t) is the short-term feedback control factor, and ζ(t) is the short-term optimization adjustment factor;

[0114] S83. In the long-term feedback loop, the system combines historical production data and the current state of process parameters to perform trend analysis and optimization of process parameters throughout the production cycle:

[0115]

[0116] Among them, λ opt (t + 1, X) is the combination of process parameters optimized by long-term feedback, κ l (t) is the long-term feedback adjustment factor, and P t+1 are the system response gradient and path update result, β(t) is the feedback adjustment coefficient, and F(λ(t, X)) is the feedback correction function;

[0117] S84. Through the multi-level feedback loop, the system can simultaneously perform short-term and long-term process parameter adjustments during the production process. The short-term feedback is used to correct the immediate deviations in production in real-time, while the long-term feedback is optimized throughout the production cycle to optimize the overall quality and production efficiency of the product;

[0118] S85. Apply the combination of process parameters optimized by short-term and long-term feedback to the actual production process, continuously monitor the production data, and maintain the process parameters in the optimal state through a dynamic multi-level feedback mechanism.

[0119] Example 1:

[0120] To verify the feasibility of the present invention in implementation, the present invention is applied to a precision manufacturing company located in Shanghai to optimize the forming process of its micro spring washers. This company mainly provides micro spring washers for high-end electronic equipment, and such products have extremely high requirements for forming accuracy and consistency. However, the traditional forming process has obvious deficiencies in dealing with these challenges, mainly manifested as difficult-to-control forming accuracy, low production efficiency, and serious material waste. Therefore, this company decides to introduce an efficient forming method for micro spring washers applying the ant colony algorithm of the present invention to optimize the production process.

[0121] In this embodiment, we first set the initial process parameter range according to the specific forming requirements of the micro spring washers and clarified the optimization objectives, covering key factors such as forming accuracy, production efficiency, and material utilization rate. To ensure accuracy priority during the production process, we set corresponding weight coefficients for each optimization objective.

[0122] Subsequently, the company used the ant colony optimization model to construct the initial solution space, initialized the ant colony, and set the path selection probability, pheromone update rule, heuristic factor, and pheromone evaporation coefficient. On this basis, we applied the spatio-temporal ripple propagation algorithm. By simulating the propagation effect of ripples in the solution space, we guided the ant colony to preferentially explore the high-potential areas with higher ripple intensity, thereby screening out the preliminarily optimized process parameter combinations. This step effectively narrowed the search scope and significantly improved the optimization efficiency.

[0123] To further optimize the process parameters, the company adopted the hyperdimensional interference optimization technology to expand the solution space to multiple dimensions, enabling the ant colony to explore in a wider space. By adaptively adjusting the search paths of the ant colony, the company successfully avoided the situation of being easily trapped in local optimal solutions in traditional methods, thus finding a better process parameter combination.

[0124] After obtaining the preliminarily optimized process parameter combinations, the company introduced the quantum superposition search technology, regarded the process parameter combinations as quantum states, and realized the parallel search of multiple potential optimization paths through the superposition, interference, and entanglement effects of quantum states, thereby further optimizing the process parameter combinations. The evolution of quantum states enabled the company to dynamically adjust the process parameters in multiple dimensions and finally obtained a more optimized parameter combination.

[0125] As the quantum superposition search technology gradually converged, the company applied the self-organized critical optimization technology to make the system enter the critical state and automatically adjust the position of the critical point according to the real-time changes of the process parameters, ensuring that the system was always in the optimal state under different production conditions. Through this method, the production efficiency and forming accuracy of the company were further improved.

[0126] In the actual production process, the company applied the optimized process parameter combinations to the production of micro spring washers and established a spatio-temporal coupling feedback mechanism. This mechanism can monitor the changes of process parameters in real time during the production process and make dynamic adjustments based on the data in the time and space dimensions. Through this mechanism, the company can immediately detect and correct the parameter deviations in production, thus ensuring the stability and consistency of the production process.

[0127] Finally, the company also applied the reverse feedback simulation mechanism to conduct a detailed analysis of the deviations occurring in the production process and pre-adjust the process parameters in the virtual environment. Through this process, the company continuously optimized and improved the process parameters in actual production, thereby significantly improving the production efficiency and effectively reducing material waste.

[0128] Table 1: Production data of high-efficiency forming process optimization for micro spring washers

[0129]

[0130] Data shows that during the period from August 2024 to October 2024, the company located in Shanghai produced approximately 5,000 micro spring washers per day. After applying the method of the present invention, the qualified rate of the products increased from the original 93% to over 98%, and the rejection rate decreased from 7% to less than 2%. The forming accuracy increased by approximately 20%, the production efficiency increased by 15%, and the material utilization rate increased by 10%. These improvements not only significantly reduced the production cost but also enhanced the company's competitiveness in the high-end market.

[0131] In summary, the method of the present invention has shown significant optimization effects in the forming process of micro spring washers, successfully solved a number of problems in the traditional process, and provided a more efficient and reliable production solution for enterprises.

[0132] As described above, only the preferred specific embodiments of the present invention are provided, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution and inventive concept of the present invention, makes equivalent substitutions or changes, and should be covered by the protection scope of the present invention.

Claims

1. An efficient forming method for micro spring washers using ant colony algorithm, characterized in that: The steps include: S1. According to the requirements of micro spring washer forming, set the initial process parameter range and determine the optimization target; S2. Based on the set parameter range, construct an ant colony optimization model, initialize the ant colony, set the path selection probability, pheromone update rule, heuristic factor and pheromone volatility coefficient, and generate the initial solution space; S3, adopting the spatiotemporal ripple propagation algorithm, by simulating the ripple propagation effect in the solution space, guiding the ant colony to preferentially explore high-potential areas according to the intensity and propagation path of the ripples, thereby screening out the preliminary optimized process parameter combination; S4. Based on the initially screened parameter combinations, the hyper-dimensional interference optimization technology is used to expand the solution space to multiple dimensions, so that the ant colony can explore potential global optimal solutions in multi-dimensional space and adaptively adjust the search path; S5. In the expanded multi-dimensional solution space, combined with quantum superphase search technology, the process parameter combination is regarded as a quantum state. Through the superposition, interference and entanglement effects of quantum states, multiple potential optimization paths are searched in parallel to further optimize the process parameter combination; S6. With the convergence of quantum superphase search technology, the self-organized critical optimization technology enables the system to further approach the global optimal solution by adaptively adjusting the process parameter combination in the critical state; S7. Apply the obtained optimal process parameter combination to the actual production process, adopt the time-space coupling feedback mechanism, combine the data of time and space dimensions in the production process, and conduct real-time monitoring and dynamic adjustment of the process parameter changes in the molding process; S8. In the actual production process, the reverse feedback simulation mechanism is applied to analyze the deviations that occur in the production process, and the process parameters are pre-adjusted in the virtual environment to optimize and improve the subsequent production process.

2. The method for efficiently forming micro spring washers using ant colony algorithm according to claim 1, characterized in that: The S3 specifically includes: S31, by establishing a multi-dimensional model of the solution space, using the spatiotemporal ripple propagation algorithm to initialize the solution space, generating initial ripples, the strength of the initial ripples is determined according to the initial fitness value of the process parameter combination; S32. Based on the strength of the initial ripples, a multi-level ripple propagation model is applied to perform coarse-grained first-layer ripple propagation, and by simulating the propagation of ripples in the solution space, a first-layer ripple map is generated, and a preliminary excellent process parameter area is determined; S33. Generate a second layer of ripples in the determined preliminary good area, and perform a more fine-grained search through the second layer of ripple propagation: Among them, I2(x, t) represents the intensity of the second layer of ripples in the good area, I1(x, t) is the intensity of the first layer of ripples, α, β, γ, θ, δ are nonlinear dynamic parameters for adjusting the ripple intensity, is the gradient modulus of the first layer ripple intensity, represents the second-order derivative of the first layer ripple intensity with respect to time; S34, according to the intensity distribution of the second layer of ripples, guide the ant colony to preferentially explore the high-potential areas with higher intensity, and select the best search route in the solution space according to the ripple propagation path and intensity change; S35. Through the layer-by-layer refinement of the multi-level ripple propagation model and the collaborative search of the ant colony, a preliminary optimized process parameter combination is finally screened out, which will serve as the basis for further optimization in subsequent steps.

3. The method for efficiently forming micro spring washers using ant colony algorithm according to claim 1, characterized in that: The S4 specifically includes: S41. Based on the initially screened parameter combinations, an extended solution space model is constructed to form a multidimensional solution space by adding additional dimensions; S42, in the multidimensional solution space, initializing the search path of the ant colony, and adjusting the initial direction and step length of each path according to the initial conditions in each dimension; S43. In the multi-dimensional solution space, the hyper-dimensional interference optimization technology is used for the adjusted initialization path to dynamically adjust the search path of the ant colony, and combined with the spontaneous symmetry breaking mechanism, more search directions are obtained: Among them, P t+1 is the position of the path at step t+1, P t is the position of the path at step t, η and ζ are the adjustment parameters for path update, I2(x,t) is the second layer ripple propagation strength, M t is the interference matrix of the path, W t is the weight matrix, is the gradient of the fitness function, D t is the path adjustment direction matrix, ξ is the regulation factor of the spontaneous symmetry breaking mechanism, ΔS t is the perturbation vector caused by spontaneous symmetry breaking; S44, at each step of the search path update, dynamically calculate the interference matrix M on the path t ,By combining the path optimization guided by spontaneous symmetry breaking, the ant colony can break the symmetry in the solution space and explore more potential optimal solution areas; S45. The search path is adaptively adjusted through the optimized search of the path in the multi-dimensional solution space and the path correction guided by spontaneous symmetry breaking.

4. The method for efficiently forming micro spring washers using ant colony algorithm according to claim 1, characterized in that: The S6 specifically includes: S61. In the process of gradual convergence of quantum superphase search technology, the self-organized critical optimization technology is used to make the system enter the critical state, and the position of the critical point is automatically adjusted according to the real-time changes of process parameters to adapt to different production conditions and needs; S62, introduce a critical point dynamic adjustment mechanism, through real-time monitoring of production data and process parameter combination changes, the system can identify the current state and the initial critical point λ c The distance between the critical points is adjusted dynamically: Among them, λ c (t+1) is the critical point position after dynamic adjustment at the t+1th moment, λ c (t) is the critical point position at time t, α(t) is the adjustment factor at time t, is the system state gradient of the current process parameter combination, β(t) is the feedback adjustment coefficient at time t, I2(x,t) is the generated second-layer ripple propagation intensity, and F(λ(t)) is the correction function of the feedback control system; S63. During the dynamic adjustment of the critical point, the system continuously corrects and optimizes the process parameters through adaptive adjustment according to the state of the combination of real-time production data and process parameters; S64. After each adjustment, the system analyzes the new critical point λ c (t+1) affects the process parameter combination, evaluates the system status in real time and updates the optimization path, gradually approaching the global optimal solution.

5. The method for efficiently forming micro spring washers using ant colony algorithm according to claim 1, characterized in that: The S7 specifically includes: S71. Apply the obtained optimal process parameter combination to the actual production process and establish a spatiotemporal coupling feedback mechanism model; S72. Introducing a multi-level collaborative ant colony algorithm into the spatiotemporal coupling feedback mechanism, the optimization task of the process parameter combination λ(t,X) is divided into multiple levels, each level corresponding to a different production target; S73. At each level of the multi-level collaborative ant colony algorithm, process parameter data related to time t and spatial position X in the production process are collected in real time, and these data are input into the feedback control system: Among them, λ(t+1,X) is the process parameter combination at the t+1th time and the spatial position X, γ(t) is the time-space coupling feedback control factor, is the gradient of the system state function to the process parameter combination, δ(t) is the feedback adjustment coefficient in the time dimension, is the rate of change of the process parameter combination over time, ξ(t) is the adjustment factor; S74. During the production process, a multi-level collaborative ant colony algorithm is used to adjust the state of the process parameter combination in real time. When the system detects that the process parameter combination deviates from the optimal state, the ant colonies at each level work together to make corrections through the feedback control system to return the parameter combination to the optimal path; S75. Combined with the operating data of the production equipment, the system state function S(λ(t,X)) is dynamically optimized, and the process parameter combination is kept in the optimal state in the dynamic production environment by dynamically adjusting the critical point.

6. The method for efficiently forming micro spring washers using ant colony algorithm according to claim 1, characterized in that: The S8 specifically includes: S81. In the actual production process, a multi-level reverse feedback simulation mechanism is applied to divide the process parameter deviations that occur in the production process into short-term deviations and long-term deviations, and to establish short-term feedback loops and long-term feedback loops respectively, so as to adjust the process parameter optimization requirements at different time scales; S82. In the short-term feedback loop, real-time acquisition of process parameter data related to time and space position in the production process is performed, and the immediate process parameter deviation Δλ is calculated. s (t,X): Among them, λ new (t+1,X) is the adjusted process parameter combination at the t+1th time and spatial position X, κ s (t) is the short-term feedback adjustment factor, γ(t) is the short-term feedback control factor, and ζ(t) is the short-term optimization adjustment factor; S83. In the long-term feedback loop, the system combines historical production data and current process parameter status to perform trend analysis and optimization of process parameters throughout the production cycle: Among them, λ opt (t+1,X) is the process parameter combination after long-term feedback optimization, κ l (t) is the long-term feedback adjustment factor, and P t+1 is the system response gradient and path update result, β(t) is the feedback adjustment coefficient, and F(λ(t,X)) is the feedback correction function; S84. Through multi-level feedback loops, the system can make short-term and long-term process parameter adjustments during the production process. Short-term feedback is used to correct immediate deviations in production in real time, while long-term feedback is optimized throughout the entire production cycle to optimize the overall quality and production efficiency of the product. S85. Apply the process parameter combination optimized by short-term and long-term feedback to the actual production process, and continuously monitor the production data to keep the process parameters in the optimal state through a dynamic multi-level feedback mechanism.

Citation Information

Cited By

  • Microalloying high-strength steel production system

    CN121390600A