Controllable-pitch propeller dehydrogenation process optimization method based on reliability model

Abstract

In order to solve the defects in the prior art, the invention discloses a controllable-pitch propeller dehydrogenation process optimization method based on a reliability model, which comprises the following steps: constructing a controllable-pitch propeller reliability model based on a stress-strength interference model, taking a strength limit and environmental stress as random variables, and quantifying reliability through probability density function joint integration; with reliability maximization as a target, an optimization model including electroplating interval time, dehydrogenation heating time and dehydrogenation temperature is established, random error influences of man-machine material ring elements are incorporated, and constraint conditions are set; a GA-HC algorithm is adopted to solve the model, global search of a genetic algorithm is combined with local fine search of a hill-climbing algorithm, and the crossover rate and the mutation rate are dynamically adjusted to improve the solving efficiency. The method aims at solving the problems that a traditional dehydrogenation process depends on experience setting and uncertainty cannot be quantified, and a data-driven optimization scheme is provided for high-quality manufacturing of the controllable-pitch propeller.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of reliability engineering, and more particularly to a propeller dehydrogenation process optimization method based on a reliability model. BACKGROUND

[0002] The propeller is the core component of the ship propulsion system, and its performance is directly related to the maneuverability, reliability and safety of the ship. In the quality control system of the propeller throughout its life cycle, the improvement of product reliability involves design optimization, precision manufacturing, quality testing and other key links. Based on the completion of the structure and fluid dynamics design, the process level of the production and manufacturing link plays a decisive role in the final performance indicators of the propeller in its manufacturing process. In order to enhance the surface properties such as corrosion resistance and wear resistance, surface treatment such as electroplating is often required for key components such as blades and hubs. However, the electroplating process can cause a large amount of hydrogen to penetrate into the metal matrix, leading to hydrogen embrittlement of the material, i.e. a significant decrease in the plasticity and toughness of the material, which is prone to brittle fracture under stress, posing a serious threat to the service safety of the propeller. Therefore, after electroplating, sufficient dehydrogenation treatment must be carried out to eliminate the hydrogen embrittlement hazard. Currently, the industry generally uses heating and baking to dehydrogenate. The core parameters of the dehydrogenation process mainly include dehydrogenation temperature, holding time and time interval from electroplating completion to dehydrogenation start.

[0003] However, the existing dehydrogenation process parameter setting method mainly relies on process manuals, empirical formulas or the practical experience of operators, which makes it difficult to accurately match specific product structures, material batches and equipment states, resulting in a blurred process window and low optimization degree. In addition, traditional process design regards material strength and process stress as deterministic values, without fully considering the randomness and uncertainty brought by "man-machine-material-method-environment" and other factors in actual production.

[0004] In summary, how to establish a scientific and quantitative method to comprehensively consider various uncertainty factors and optimize the dehydrogenation process in a front-end and systematic manner to achieve and ensure the target reliability required by the product is a technical problem to be solved in the field. SUMMARY

[0005] The present application provides a propeller dehydrogenation process optimization method based on a reliability model, which overcomes the problems of the prior art and is characterized by the following steps:

[0006] (1) Construct a propeller reliability model R(S, E) based on a stress-strength interference model; the reliability model based on the stress-strength interference model is the probability that the strength limit S of the propeller is greater than the environmental stress E.

[0007] The reliability R of the adjustable propeller is preferably defined as the probability P that the strength limit S of the adjustable propeller is greater than the environmental stress E, i.e.

[0008] R(S,E) = P(S>E) = P(S-E>0) Equation 1

[0009] The environmental stress and the strength limit of the workpiece in actual working conditions are both random variables, and their probability density functions are f(S) and h(E), respectively. The interference region of the two may have a case of S

[0010] It is assumed that when the environmental stress is E0, the probability that the strength limit is greater than the environmental stress is

[0011]

[0012] The probability that the environmental stress is in the interval dE is

[0013]

[0014] where dE is the differential form of the environmental stress;

[0015] It is assumed that S>E0 and E0-dE / 2≤E≤E0+dE / 2 are two independent events, and the probability that the two independent events occur simultaneously is

[0016]

[0017] where dR is the differential form of the reliability of the adjustable propeller;

[0018] Considering the entire stress interval, the reliability of the adjustable propeller can be expressed as

[0019]

[0020] It is assumed that the strength limit S follows a normal distribution with parameters , which is denoted as The environmental stress E follows a normal distribution with parameters , which is denoted as It is assumed that the safety margin Z=S-E follows a normal distribution with parameters , i.e.

[0021]

[0022] where Z = μ S - μ E ,

[0023] The reliability model of the adjustable propeller represented by the normal distribution function is

[0024]

[0025] where dZ is the differential form of the safety margin.

[0026] (2) Constructing the propeller hydrogen removal process optimization model; the propeller hydrogen removal process optimization model is a hydrogen removal process parameter optimization model with the maximum propeller reliability as the target.

[0027] Preferably, the propeller reliability model R(S, E) constructed in the previous step is used as the optimization target, and the maximization of R(S, E) is pursued, and the objective function is represented as

[0028]

[0029] The strength limit of the propeller after the hydrogen removal process introduces the random error influence of the man-machine-material-loop elements, wherein the selection of the process parameters is the plating interval time d(h), the hydrogen removal heating time t(h) and the hydrogen removal temperature T(℃), and is represented as

[0030]

[0031] wherein is the approximate relationship model between the strength limit and the key parameters of the hydrogen removal process, namely the plating interval time d(h), the hydrogen removal heating time t(h) and the hydrogen removal temperature T(℃), which is calculated from historical test data, ε is a random error, which is subject to normal distribution, and the mean μ ε , the variance The influence relationship with the man-machine-material-loop elements is represented as

[0032]

[0033] wherein x i represents the i-th man-machine-material-loop element, is the mean of x i ;

[0034] Considering the process requirements, the process parameters and the strength limit need to be within the process specification range during the optimization process, that is, the constraint condition is set as

[0035]

[0036] wherein S min , S max respectively represent the upper and lower limits of the strength limit, d min , d max respectively represent the upper and lower limits of the plating interval, t min , t max respectively represent the upper and lower limits of the hydrogen removal heating time, T min , T maxrespectively represent the upper and lower limits of the temperature of removing hydrogen; the constructed process optimization model is represented as:

[0037]

[0038] d min ≤d≤d max

[0039] t min ≤t≤t max

[0040] T min ≤T≤T max Formula 14

[0041] (3) the GA-HC algorithm is used to solve the hydrogen removal process parameter optimization model in the previous step; the GA-HC algorithm is a genetic algorithm (Genetic Algorithm, GA) optimized by using the hill-climbing algorithm (Hill-Climbing, HC).

[0042] Preferably, the GA-HC algorithm performs global search through GA to explore the solution space, and combines the local fine search capability of HC to improve the accuracy of the solution, and the core solving idea can be represented as

[0043] min X F(X)=min X {1-R(X)} Formula 15

[0044] Where X=[d,t,T] is a process parameter vector, R(X) is a reliability function of the adjustable propeller, and F(X) is a transformed objective function;

[0045] The crossover rate p c is set in the solving process. With the dynamic adjustment of the fitness of the population individuals, the adjustment process is represented as

[0046]

[0047] Where p c1 is the maximum crossover rate, p c2 is the minimum crossover rate, f' is the fitness of the parent individual, f max and f avg are the maximum fitness and average fitness of the current population, respectively.

[0048] The mutation rate p c is set in the solving process. With the dynamic adjustment of the fitness of the population individuals, the adjustment process is represented as

[0049]

[0050] Where p m1 is the maximum crossover rate, pm2 f' is the fitness of the parent individual, f max and f avg are the maximum fitness and average fitness of the current population, respectively.

[0051] The specific content of optimizing the GA by using the HC preferably includes:

[0052] For the elite individual X0 generated by the GA, a local search field is set

[0053] N(X0) = {X0 ± Δd, X0 ± Δt, X0 ± ΔT}, Equation 18

[0054] An initial fitness F(X0) is calculated; the F(X') of each candidate solution X' in the field is calculated; if there is F(X') < F(X0), X0 is updated as X', otherwise the local search is terminated.

[0055] The present application has at least one of the following advantages:

[0056] 1. The present application introduces a stress-strength mathematical reliability model, taking the strength limit and environmental stress in the hydrogen removal process as random variables, and quantifies the reliability by joint integral of the probability density function, so that the process design is changed from the traditional "engineering experience driven" to "data and model calculation driven", avoiding the subjectivity of the experience method, and the process reliability is quantitatively evaluated;

[0057] 2. The present application takes the factors influencing the quality such as man-machine-material and environment as random variables into the model, quantifies the influence of random error, and optimizes the process by comprehensively considering the fluctuation characteristics of each factor, so that the obtained process parameters have stronger anti-interference ability, can effectively contain the parameter fluctuation, environmental change and other uncertainties in actual production, and ensure that the hydrogen removal process remains stable and reliable under complex working conditions, and improves the service robustness of the pitch propeller parts;

[0058] 3. The present application covers a wide solution space by the global exploration ability of the genetic algorithm, and improves the precision of the solution by combining the local fine search of the hill climbing algorithm, forms an effective balance between global exploration and local optimization, avoids premature convergence of the genetic algorithm or local optimum of the hill climbing algorithm, greatly improves the global search success rate of the reliability optimization, and dynamically adjusts the crossover rate and mutation rate based on the population evolution state, enhances the population diversity by high parameters in the early stage, reduces the parameters for fine optimization in the later stage, significantly improves the solving efficiency, and effectively adapts to the engineering needs of the pitch propeller hydrogen removal process. BRIEF DESCRIPTION OF DRAWINGS

[0059] Figure 1 Fig. 1 shows a flowchart of the process optimization method provided by the present application;

[0060] Figure 2A schematic diagram of reliability provided by the present application by joint integration of the probability density function of the strength limit and environmental stress is shown.

[0061] Figure 3 A schematic diagram of the GA-HC algorithm solving process provided by the present application is shown.

[0062] Figure 4 A schematic diagram of the mean square error change process in the approximate relationship model training process between the strength limit and the process parameters provided by the present application is shown.

[0063] Figure 5 A schematic diagram of the fitness change in the GA-HC algorithm iteration operation process provided by the present application is shown. DETAILED DESCRIPTION

[0064] The present application will now be further described in detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams and only illustrate the basic structure of the present application in a schematic manner, and therefore only show the configurations related to the present application.

[0065] Please note that the "upper", "lower", "left", "right", "top end", "top", "bottom end", "bottom" and the like used by the present application to describe the positional relationship do not represent the absolute positional relationship between the modules / components / elements / units / parts, but the relative positional relationship between the modules / components / elements / units / parts.

[0066] As Figure 1 shown, the present application exemplarily provides a propeller dehydrogenation process optimization method based on a reliability model, comprising the following steps:

[0067] Step one, build a propeller reliability model R(S, E) based on a stress-strength interference model; the reliability model based on the stress-strength interference model is the probability that the strength limit S of the propeller is greater than the environmental stress E, as Figure 2 shown.

[0068] Preferably, the strength limit of the product is S, the use environmental stress is E, and the propeller reliability R under normal working conditions of the propeller is the probability P that the strength limit S is greater than the environmental stress E, which is expressed as

[0069] R(S, E) = P(S > E) = P(S - E > 0) Equation 1

[0070] It is assumed that the use environmental stress and the workpiece strength limit of the propeller in the actual working condition are both random variables, and the probability density functions thereof are f(S) and h(E), respectively. The interference region of the two may appear S < E, which leads to failure of the propeller.

[0071] The probability that the strength limit is greater than the environmental stress when the environmental stress is E0 is set as P (S > E0)

[0072]

[0073] The probability that the environmental stress is in the dE interval is P (E0-dE / 2 ≤ E ≤ E0+dE / 2)

[0074]

[0075] where dE is a differential form of the environmental stress;

[0076] The probability that the two independent events occur simultaneously is P (S > E0 and E0-dE / 2 ≤ E ≤ E0+dE / 2) = P (S > E0) * P (E0-dE / 2 ≤ E ≤ E0+dE / 2)

[0077]

[0078] where dR is a differential form of the propeller reliability;

[0079] Considering the entire stress interval, the propeller reliability can be expressed as P (R) = ∫P (S > E0 and E0-dE / 2 ≤ E ≤ E0+dE / 2) dE

[0080]

[0081] It is assumed that the strength limit S follows a normal distribution with parameters , denoted as The environmental stress E follows a normal distribution with parameters , denoted as The safety margin Z = S-E is set, and Z also follows a normal distribution with parameters , that is,

[0082]

[0083] where Z = μ S - μ E ,

[0084] The propeller reliability model represented by the normal distribution function is P (R) = ∫P (S > E0 and E0-dE / 2 ≤ E ≤ E0+dE / 2) dE = ∫P (Z > 0) dZ

[0085]

[0086] where dZ is a differential form of the safety margin.

[0087] Step two, constructing a propeller hydrogen removal process optimization model; the propeller hydrogen removal process optimization model is a hydrogen removal process parameter optimization model with the goal of maximizing propeller reliability.

[0088] The reliability model R(S, E) of the adjustable pitch propeller built in the last step is preferably used as an optimization target to maximize R(S, E), and the objective function is expressed as

[0089]

[0090] The strength limit of the adjustable pitch propeller after the hydrogen removal process introduces the random error influence of the man-machine-material-loop elements, wherein the process parameters are selected as the plating interval time d(h), the hydrogen removal heating time t(h), and the hydrogen removal temperature T(℃), and are expressed as

[0091]

[0092] wherein is an approximate relationship model between the strength limit and the key parameters of the hydrogen removal process, including the plating interval time d(h), the hydrogen removal heating time t(h), and the hydrogen removal temperature T(℃), which is calculated based on historical test data, ε is a random error, and is subject to a normal distribution with a mean of 0 and a variance of ; and the mean μ ε and the variance are expressed as

[0093]

[0094] wherein x i represents the i-th man-machine-material-loop element, is the mean of x i .

[0095] Considering the process requirements, the process parameters and the strength limit need to be within the process specification range during the optimization process, that is, the constraint conditions are set as

[0096]

[0097] wherein S min and S max respectively represent the upper and lower limits of the strength limit, d min and d max respectively represent the upper and lower limits of the plating interval, t min and t max respectively represent the upper and lower limits of the hydrogen removal heating time, and T min and T max respectively represent the upper and lower limits of the hydrogen removal temperature. According to the historical data of a certain adjustable pitch propeller, the approximate relationship model between the strength limit S and the plating interval time d(h), the hydrogen removal heating time t(h), and the hydrogen removal temperature T(℃) is obtained by BP neural network nonlinear fitting The mean square error change process during the training process is shown in Figure 4 .

[0098] The constructed process optimization model is represented as

[0099]

[0100] d min ≤d≤d max

[0101] t min ≤t≤t max

[0102] T min ≤T≤T max Equation 14

[0103] Step three, the GA-HC algorithm is used to solve the hydrogen removal process parameter optimization model in the previous step; the GA-HC algorithm is a genetic algorithm (Genetic Algorithm, GA) optimized by using the hill-climbing algorithm (Hill-Climbing, HC).

[0104] Preferably, the GA-HC algorithm performs global search through GA to explore the solution space, and combines the local fine search capability of HC to improve the accuracy of the solution, and the algorithm process is as shown in Figure 3 The core solving idea can be represented as

[0105] min X F(X)=min X {1-R(X)} Equation 15

[0106] Where X=[d, t, T] is the process parameter, R(X) is the reliability function of the adjustable pitch propeller, and F(X) is the transformed objective function;

[0107] The crossover rate p c is set during the solving process With the dynamic adjustment of the fitness of the population individuals, the adjustment process is represented as

[0108]

[0109] Where p c1 is the maximum crossover rate, p c2 is the minimum crossover rate, f' is the fitness of the parent individual, f max and f avg are the maximum fitness and average fitness of the current population, respectively;

[0110] The mutation rate p c is set during the solving process With the dynamic adjustment of the fitness of the population individuals, the adjustment process is represented as

[0111]

[0112] Where p m1 is the maximum crossover rate, pm2 f' is the fitness of the parent individual, f max and f avg are the maximum fitness and the average fitness of the current population, respectively.

[0113] The specific content of optimizing GA by HC preferably includes:

[0114] For the elite individual X0 generated by GA, set the local search field

[0115] N(X0) = {X0 ± Ad, X0 ± At, X0 ± AT}, Equation 18

[0116] Calculate the initial fitness F(X0); calculate F(X') for each candidate solution X' in the field N(X0); if there exists F(X') < F(X0), update X0 = X', otherwise terminate the local search.

[0117] Example 2

[0118] In this embodiment, the constraint conditions are 0 < d < 4h for the plating interval time, 12h < t < 21h for the hydrogen removal time, and 180℃ < T < 200℃ for the temperature; considering the influence of the man-machine-material-environment elements, the influence of man-machine-material-environment is added to the strength limit S in the form of a random error ε, and the random error ε obeys a normal distribution with a mean of 0 and a variance of 5, denoted as ε ~ N(0, 5), and the strength limit of the pitch prop after considering the random error cannot exceed its process requirement S < 1050MPa, so the hydrogen removal process parameter optimization process is:

[0119] 1. Construct a reliability model R(S, E) of the pitch prop based on the stress-strength interference model; the reliability model of the hydrogen removal process based on the stress-strength interference model is the probability that the strength limit S of the pitch prop is greater than the environmental stress E, S, as shown in Figure 2 ;

[0120] 2. Construct a pitch prop hydrogen removal process optimization model; the pitch prop hydrogen removal process optimization model is a hydrogen removal process parameter optimization model with the goal of maximizing the reliability of the pitch prop; the optimization variables are the plating interval time d (h), the hydrogen removal heating time t (h), and the hydrogen removal temperature T (℃); according to the above constraint conditions, the process optimization model can be expressed as:

[0121]

[0122] s.t. S = f(t1, t2, T) + ε < 1050MPa

[0123] 0 < t1 < 4h

[0124] 12h < t1 < 21h

[0125] 180C° ≤ T ≤ 200C°

[0126] 3. Using GA-HC algorithm to solve the hydrogen removal process parameter optimization model in the last step; further local search on the elite individuals obtained by GA algorithm through HC algorithm; setting the maximum iteration number in the algorithm as 100, the population size as 100, the initial crossover rate p c = 0.9 and the initial mutation rate p m = 0.1, and the chromosome individual using decimal encoding mode.

[0127] The fitness change of the algorithm iteration operation is shown in the following table. Figure 5 The fitness value basically remains unchanged after the algorithm iteration to the 23rd time, at this time the maximum fitness is 99.927, at this time the corresponding hydrogen removal temperature is 193℃, the hydrogen removal time is 15h, and the plating interval time is 2.5h.

[0128] Based on the above ideal embodiments according to the present application, through the above description, relevant staff can make various changes and modifications without deviating from the technical idea of the present application. The technical scope of the present application is not limited to the content in the specification, and the technical scope must be determined according to the scope of claims.

Claims

1. An optimization method for hydrogen removal process of controllable pitch propeller based on a reliability model, characterized in that, Includes the following steps: (1) Construct a reliability model R(S,E) for the controllable pitch propeller based on the stress-strength interference model, where R(S,E) represents the probability that the strength limit S of the controllable pitch propeller is greater than the environmental stress E. (2) Construct an optimization model for the hydrogen removal process of the controllable pitch propeller with the goal of maximizing reliability; (3) The genetic algorithm optimized by the hill climbing algorithm is used to solve the hydrogen removal process optimization model of the pitch propeller and output the optimal hydrogen removal process parameters.

2. The method for optimizing the hydrogen removal process of a controllable-pitch propeller based on a reliability model according to claim 1, characterized in that, The construction process in step (1) includes: (101) Define the reliability R of the controllable pitch propeller as the probability P that its strength limit S is greater than the environmental stress E, i.e. R(S,E)=P(S>E)=P(SE>0) Formula 1 (102) Set the environmental stress and workpiece strength limit of the controllable pitch propeller in actual working conditions as random variables, with probability density functions f(S) and h(E) respectively. The interference region between the two may have S < E, which leads to the failure of the controllable pitch propeller. Let the probability that the ultimate tensile strength exceeds the environmental stress be set to E0. Where dS is the differential form of the strength limit, and the probability that the environmental stress is within the dE interval is: Where dE is the differential form of the environmental stress; Let S > E0 and E0 - dE / 2 ≤ E ≤ E0 + dE / 2 be two independent events. Then the probability of these two independent events occurring simultaneously is: Where dR is the differential form of the controllable pitch propeller reliability; Considering the entire stress range, and combining the joint integral of the probability density function, the reliability of the controllable pitch propeller can be expressed as:

3. The optimization method for hydrogen removal process of controllable pitch propeller based on a reliability model according to claim 2, characterized in that: Assume the ultimate tensile strength S follows the parameter... The normal distribution is denoted as . The environmental stress E all obey the parameter . The normal distribution is denoted as . If the safety margin is set to Z = SE, then Z also follows the parameter... The normal distribution, i.e. among them Z =μ S -m E , The reliability R can be obtained by calculating using the normal distribution function. Where dZ is the differential form of the safety margin.

4. The optimization method for hydrogen removal process of controllable pitch propeller based on a reliability model according to claim 3, characterized in that, The construction process in step (2) includes: (201) According to Equation 7, the objective function of the hydrogen removal process optimization model is: (202) Set constraints, let This is an approximate model showing the relationship between ultimate strength and process parameters, where ε is a random error following a normal distribution with a mean of μ. ε and variance Related to human, machine, material, and environmental factors, the ultimate strength S is expressed as: The strength limit range can then be obtained as follows: Where S min ,S max These represent the upper and lower limits of the strength limit, respectively; A process optimization model is constructed by combining process parameters and strength limit range.

5. The optimization method for hydrogen removal process of controllable pitch propeller based on a reliability model according to claim 4, characterized in that, set up This is an approximate model showing the relationship between the ultimate tensile strength and the dehydrogenation process parameters: electroplating time d (h), dehydrogenation heating time t (h), and dehydrogenation temperature T (°C); ε represents a random error following a normal distribution. The range of the ultimate tensile strength S is then expressed as: The strength limit range can then be obtained as follows: Where S min ,S max These represent the upper and lower limits of the strength limit, respectively; The process parameter range is as follows: Where d min ,d max These represent the upper and lower limits of the electroplating interval, t. min ,t max T represents the upper and lower limits of the hydrogen removal heating time, respectively. min ,T max These represent the upper and lower limits of the hydrogen removal temperature, respectively. The constructed process optimization model is represented as follows: d min ≤d≤d max t min ≤t≤t max T min ≤T≤T max Equation 14.

6. The optimization method for hydrogen removal process of controllable pitch propeller based on a reliability model according to claim 3, characterized in that, The solution process of the GA-HC algorithm in step (3) includes: (301) Transform the objective function according to the GA algorithm. min X F(X) = min X {1-R(X)} Equation 15 Where X = [d, t, T] are the process parameters, R(X) is the reliability function of the controllable pitch propeller, and F(X) is the converted objective function; (302) Set dynamic adjustment of cross rate: Where p c1 For the maximum crossover rate, p c2 f is the minimum crossover rate, f′ is the fitness of the parent individual, f max and f avg These are the current population's maximum fitness and average fitness, respectively. (303) Set the dynamic adjustment of the mutation rate: Where p m1 For the maximum crossover rate, p m2 This represents the minimum crossover rate. (304) The HC algorithm is used to optimize the GA algorithm. The optimization process is as follows: (3041) Define a local search domain for the elite individual X0 generated by GA: N(X0)={X0±Δd,X0±Δt,X0±ΔT} Equation 18 (3042) Calculate the initial fitness F(X0). For each candidate solution X′∈N(X0) in the neighborhood, calculate F(X′). If there exists F(X′)<F(X0), then update X0=X′; otherwise, terminate the search.

Images