CN107169165B - Surface modification process reliability evaluation method based on environmental effect - Google Patents

Surface modification process reliability evaluation method based on environmental effect Download PDF

Info

Publication number
CN107169165B
CN107169165B CN201710244055.0A CN201710244055A CN107169165B CN 107169165 B CN107169165 B CN 107169165B CN 201710244055 A CN201710244055 A CN 201710244055A CN 107169165 B CN107169165 B CN 107169165B
Authority
CN
China
Prior art keywords
degradation
integrity
environment
data
stress
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201710244055.0A
Other languages
Chinese (zh)
Other versions
CN107169165A (en
Inventor
戴伟
尹昌
迟永娇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beihang University
Original Assignee
Beihang University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beihang University filed Critical Beihang University
Priority to CN201710244055.0A priority Critical patent/CN107169165B/en
Publication of CN107169165A publication Critical patent/CN107169165A/en
Application granted granted Critical
Publication of CN107169165B publication Critical patent/CN107169165B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computer Hardware Design (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Geometry (AREA)
  • Data Mining & Analysis (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Testing Resistance To Weather, Investigating Materials By Mechanical Methods (AREA)

Abstract

The invention provides a surface modification process reliability evaluation method based on environmental effect, which comprises the following steps: firstly, the method comprises the following steps: analyzing the integrity characteristics of the key surface and the stress of the sensitive environment; II, secondly: critical surface integrity feature degradation experiments; thirdly, the method comprises the following steps: establishing a degradation prediction model; fourthly, the method comprises the following steps: predicting the degradation of the integrity characteristics of the key surface in a dynamic environment; fifthly: calculating an evaluation index; through the steps, the degradation process of the key surface integrity feature in the dynamic environment can be accurately predicted, the probability that the key surface integrity feature is larger than the degradation threshold value at a certain moment in the dynamic environment is calculated, the capability of the process for resisting the environmental stress can be evaluated, the reliability evaluation of the process is realized, and the optimization of the process flow can be helped.

Description

Surface modification process reliability evaluation method based on environmental effect
Technical Field
The invention relates to a surface modification process reliability evaluation method based on environmental effect, which can accurately predict the degradation process of key surface characteristics of a product in a dynamic natural environment, can quantitatively estimate the adaptability of a surface modification process in different environments, and realizes the evaluation of the surface modification process reliability based on the strength of the adaptability. The method is suitable for the technical fields of process reliability evaluation, maintenance decision and the like.
Background
The surface modification process is a common process method for improving the surface characteristics of products, and is a technology for improving the performance of product parts or materials by changing the chemical components or the texture structure of the surfaces of materials or workpieces by adopting a chemical and physical method. The product surface is endowed with new characteristics of high temperature resistance, corrosion resistance, wear resistance, fatigue resistance and the like, so that the reliability of the product can be improved. The reliability of the surface modification process refers to the ability of a product processed by the surface modification process to perform its intended function for a predetermined time under a predetermined condition. Reasonable process reliability evaluation on the surface modification process can ensure the reasonability of process selection, improve the matching degree of the process and the use environment, further improve the reliability of products and the like. Therefore, the quality of the process reliability evaluation method is significant to the product quality.
At present, researchers at home and abroad have more evaluation methods for manufacturing processes, but research for evaluating a surface modification process based on environmental effects from the actual use environment of products is lacked. In practical engineering applications, the failure rates of products in different working environments are greatly different, so that different process methods need to be selected for different environments. The surface integrity is an important characteristic of the comprehensive capability of the surface of the product, the degradation degree of the surface can reflect the damage degree of the surface of the product, the influence of the environmental effect on the surface integrity of the product is ignored, the product is easy to fail early, and the specified function of the product cannot be completed. Therefore, the method for evaluating the reliability of the surface modification process by exploring and considering the environmental effect has very important significance, and the research on the aspect is weak at present, so that the invention provides the method for evaluating the reliability of the surface modification process based on the environmental effect.
Disclosure of Invention
The invention provides a surface modification process reliability evaluation method based on environmental effect, which is a method for quantitatively evaluating the reliability of a surface modification process by taking the adaptive capacity of the surface modification process in a dynamic environment as a starting point based on the environmental effect. Firstly, the relationship among the failure mode, the failure mechanism and the use environment of the product needs to be analyzed, and the integrity characteristic of the key surface and the sensitive environmental stress are determined. And then applying sensitive environmental stress to the product with the modified surface, detecting and recording degradation data of the surface integrity characteristics of the product, simultaneously monitoring and recording the environmental stress during the experiment until the key surface integrity characteristics are degraded to a failure threshold value, and finishing the experiment. And then establishing a degradation prediction model of the surface integrity characteristic by using a neural network algorithm. And then, bringing the new environmental stress data and the detection data of the integrity characteristics of the key surfaces of the products into a trained prediction model to obtain the degradation data of the integrity characteristics of the surfaces under the action of the environmental stress. And calculating the probability that the key surface integrity characteristic value is greater than the failure threshold value under the action of dynamic environmental stress by combining the failure threshold value of the key surface integrity characteristic and utilizing a stress intensity interference model, and taking the probability as a surface modification process reliability evaluation index based on the environmental effect.
(1) Objects of the invention
Reasonable process reliability evaluation can ensure the reasonability of process selection, improve the matching degree of the process and the use environment, and further improve the reliability of products. In practical engineering application, the environmental effect not only influences the degradation process of the product surface, but also plays a role in screening the surface modification process technology, and the environmental effect and the process matching degree can be visually reflected. Neglecting the influence of environmental effects on the product can cause the product to be unable to complete the specified functions, reducing the service life of the product. At present, a method for evaluating a surface modification process from the viewpoint of environmental effects is lacking. The invention provides a surface modification process reliability evaluation method based on environmental effect, which is a process reliability evaluation method which is visual, simple and strong in operability and can quantitatively represent the environmental adaptability of the surface modification process.
(2) Technical scheme
The invention relates to a surface modification process reliability evaluation method based on an environmental effect. And determining the integrity characteristics of the key surface and the sensitive environmental stress by analyzing the relationship between the failure mode and the failure mechanism of the product and the environmental stress. And training a neural network by using the degradation data of the surface integrity characteristics and the sensitive environment stress data to obtain a degradation prediction model. And predicting the degradation process of the surface integrity characteristics of the product by using the dynamic environment stress data and the detection data of the surface integrity characteristics. And (3) combining the prediction data with the stress intensity interference model, and calculating the probability that the key surface integrity characteristic value is greater than the failure threshold value under the action of dynamic environmental stress to realize the evaluation of the surface modification process based on the environmental effect, wherein the specific flow of the method is shown in figure 1.
The invention relates to a surface modification process reliability evaluation method based on environmental effect, which comprises the following specific steps:
the method comprises the following steps: analyzing the integrity characteristics of the key surface and the stress of the sensitive environment; analyzing a typical failure mode of a product in a natural environment, and determining a key surface integrity characteristic C of the product according to a failure mechanism of the productiWhere i ═ 1,2, 3, …, it indicates i types of critical surface integrity characteristics such as, but not limited to, hardness, roughness, bond strength, and the like; determining the sensitive environmental stress S based on the sensitivity of the environmental stress to the degradation process of the integrity characteristics of the key surfacelWhere l is 1,2, 3, …, it means that there are l sensitive environmental stresses, such as but not limited to temperature stress S in a seawater environmentTpH value SPDissolved oxygen SDSalinity SSOxidation-reduction potential SOPRIso-environmental stress;
step two: critical surface integrity feature degradation experiments; detecting the degradation process of the product with the modified surface in the natural environment, and recording the degradation data of the product; the specific experimental method comprises the steps of firstly detecting the integrity characteristics of each key surface when the product is not degraded, and then carrying out comparison on the characteristics C of the product at intervals of degradation time delta tiOne measurement is taken until its characteristic degrades to a failure threshold. After the experiment is finished, simultaneously monitoring the stress of the sensitive environment in real time and recording data Cij，CijJ-th detection data representing the integrity characteristics of the ith type of key surface;
step three: establishing a degradation prediction model; and constructing a data vector by using the product degradation data and the environment data, wherein each sample vector of the neural network input layer is in the form of:
X＝[S1j，S2j，S3j，…，Snj，C1j，C2j，C3j，…，Cij]，
wherein: x represents a vector of samples and X represents,
n-1, 2, 3, …, indicating n sensitive environmental stresses, [ S [ ]1j，S2j，S3j，…，Snj，C1j，C2j，…，Cij]Representing a sample vector formed by the jth monitoring value of n-class environmental stress and the jth monitoring value of i-class key surface integrity characteristic; each sample vector of the output layer is Y ═ C1j，C2j，C3j，…，Cij]I ═ 1,2, 3, …; j-1, 2, 3, …, which represents the j-th inspection data for the i-type key surface integrity feature; establishing a degradation prediction model based on the surface integrity characteristics of the environmental effect by combining a neural network algorithm, and training a neural network until the precision meets the requirement to obtain the prediction model;
step four: predicting the degradation of the integrity characteristics of the key surface in a dynamic environment; bringing the new sensitive environment stress data and the degradation initial value of the key surface integrity characteristic into a degradation prediction model, and calculating the degradation prediction data of the surface integrity characteristic in the environment;
step five: calculating an evaluation index; combining a stress-intensity interference model, taking a failure threshold value of surface integrity characteristics as intensity, taking a detection value of the surface integrity characteristics as stress, calculating the probability that a key surface integrity characteristic value is greater than the failure threshold value under the action of a dynamic environment effect, comparing all key surface integrity characteristics and meeting the specified requirements, taking the minimum value as an evaluation index, and realizing the evaluation of the surface modification process based on the environment effect, wherein the calculation mode of the evaluation index I is as follows:
I＝minP(Cij＞Fi) And Cij＝Ci1-X(t) (1)
Wherein I represents the process reliability evaluation index, min represents the minimum value, FiFailure threshold, C, representing the integrity feature of the i-th class of critical surfacesi1An initial value representing the bond strength of the coating, x (t) representing the amount of degradation of the key surface integrity feature over time;
wherein, in the third step, the degradation prediction model of the surface integrity characteristic based on the environmental effect is established by combining with the neural network algorithm, the neural network is trained until the precision meets the requirement to obtain the prediction model,the method comprises the following steps: changing X to [ S ]1j，S2j，S3j，…，Snj，C1j，C2j，C3j，…，Cij]Substituting Y ═ C into the input layer of the neural network algorithm1j，C2j，C3j，…，Cij]Substituting into the output layer of the neural network algorithm, and setting the neural network structure and the iteration times, precision and learning rate of the algorithm according to specific conditions.
In step four, the method for substituting the new sensitive environment stress data and the initial value of the degradation of the key surface integrity characteristic into the degradation prediction model and calculating the degradation prediction data of the surface integrity characteristic in the environment includes the following steps: substituting the new sensitive environmental stress data and the degradation initial value of the key surface integrity characteristic into the degradation prediction model as the input layer of the model, sequentially calculating the degradation result, and then continuously iterating the degradation result and the environmental stress data to obtain the degradation process data of the key surface integrity characteristic.
Through the steps, the degradation process of the key surface integrity feature in the dynamic environment can be accurately predicted, the probability that the key surface integrity feature is larger than the degradation threshold value at a certain moment in the dynamic environment is calculated, the capability of the process for resisting the environmental stress can be evaluated, the reliability evaluation of the process is realized, and the optimization of the process flow can be helped.
(3) Advantages of the invention
i. The method for evaluating the reliability of the surface modification process based on the environmental effect is a method for evaluating the reliability of the surface modification process considering the environmental effect, can realize the quantitative characterization of the matching degree of the process and the environment, and evaluates the surface modification process from the environmental adaptability of the process.
The invention provides a surface modification process reliability evaluation method based on environmental effect aiming at a surface modification process, which can dynamically predict the degradation of the surface integrity characteristics of a modified product.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
FIG. 2 is a diagram of a neural network topology of the present invention.
FIG. 3 is a graph comparing the predicted results of the present invention with the experimental results.
FIG. 4 is a graph of the incremental bond strength degradation profile of the present invention.
FIG. 5 is a graph of predicted degradation traces of coating bond strength under different environments according to the present invention.
FIG. 6 is a graph showing the evaluation index of the present invention over time.
The numbers, symbols and codes in the figures are explained as follows:
w: neuron (see figure 2)
B: offset vector (see FIG. 2)
+: weighted summation of input values for each neuron (see FIG. 2)
*: excitation function (see FIG. 2)
0,20,40,60,80,100,120: key surface integrity feature test value (see FIG. 3)
1,5,9,13,17,21,25,29,33,37,41,45,49,53,57,61,65,69,73,77,81,85,89,93,97,101: time to degradation (see FIG. 3)
T: degradation time (see FIG. 3, FIG. 4, FIG. 6)
C: key surface integrity feature test value (see FIG. 3)
Δ X: increment of degradation (see FIG. 4)
Time: degradation time of coating (see FIG. 5)
Strength: strength (see FIG. 5)
100, 39: coating bond Strength (see FIG. 5)
I: evaluation index of reliability of surface modification process based on environmental effect (see FIG. 6)
Detailed Description
In one embodiment of the invention, a method for evaluating reliability of a surface modification process based on environmental effects is provided. Certain surface modifications are known to increase the corrosion resistance of products by adding coatings to the surface of the product. The working environment of the product is natural marine environment. And monitoring each environmental stress of the marine environment in the life cycle of the product in real time and recording the data. And simultaneously detecting the degradation condition of the coating in a seawater environment, measuring the integrity characteristics of the key surface of the coating at regular intervals for 100 times in total, wherein the degradation time delta t is 1 step length of degradation time, and recording the initial value of the bonding strength of the coating and the degradation data thereof. And training the neural network by using 100 groups of experimental data to obtain a degradation prediction model. And (4) bringing new environmental data and the initial bonding strength of the coating into a trained prediction model to obtain the degradation prediction data of the bonding strength of the coating in the environment, combining the stress strength model, and calculating the process reliability evaluation index.
The invention discloses a method for evaluating reliability of a surface modification process based on an environmental effect, which is shown in figure 1 and comprises the following specific implementation steps:
the method comprises the following steps: and analyzing the integrity characteristics of the key surface and the stress of the sensitive environment. Typical failure modes of the coatings in natural seawater environment are analyzed as coating blistering and peeling, and the bonding strength is defined as a key surface integrity characteristic according to the failure mechanism of the coatings. Determining the sensitivity of each environmental stress to the degradation process of the coating based on the sensitivity of the environmental stress of the natural marine environment to the temperature S of the seawaterTSalinity S of sea waterSDissolved oxygen S of seawaterDpH value S of seawaterPOxidation-reduction potential S of seawaterOPRFive environmental stresses.
Step two: and (4) coating bonding strength degradation experiment. Firstly, sensitive environmental stress in a natural seawater environment in the monitoring experiment process is monitored, data are recorded, see table 1, then a product with a modified surface is placed in the natural seawater environment, and the initial bonding strength B of a coating is detected0Then observing the degradation condition of the coating in the environment, measuring the bonding strength of the coating at regular intervals of degradation time delta t until the bonding strength is reduced to a failure threshold value of the bonding strength of the coating, recording degradation data B of the bonding strength for 100 times in totaliSee table 1, where Num in table 1 represents the number of times of detection of the key surface integrity index of the coating, and c, mg/L, ppt, mV, and MPa are units of temperature, dissolved oxygen, salinity, redox site, and coating bonding strength in sequence.
Table 1 seawater environment monitoring data and 100 times of detection data of bond strength degradation
Figure BDA0001270137690000071
Figure BDA0001270137690000081
Figure BDA0001270137690000091
Figure BDA0001270137690000101
Step three: and (5) establishing a degradation prediction model. Constructing the degradation data of the bonding strength of the coating and the sensitive environmental stress as input vectors of the output layer of the neural network, wherein each measured value C of the bonding strengthiC as the next input vectori-1And sequentially iterating, and substituting the input vector into the input layer X ═ ST、SP、SD、SS、SOPR，Bi-1]. Measured value C of bonding strengthiSubstituting input layer Y ═ Ci]The neural network used in the invention comprises an input layer, a hidden layer and an output layer, the specific structure is shown in figure 2, the comparison effect of the predicted data and the actual data is shown in figure 3, and the prediction precision of the neural network is higher as can be seen from the figure. The degradation prediction of the bonding strength of the coating in different environments can be realized by utilizing a degradation prediction model considering the environmental effect.
Table 2 bond strength degradation prediction data
Figure BDA0001270137690000102
Figure BDA0001270137690000111
Step four: degradation prediction data that takes into account environmental effects. And (3) substituting the new initial degradation values of the environmental stress and the bonding strength into a degradation prediction model until the bonding strength is degraded to a failure threshold value of 39Mpa, iterating for 100 times in total, obtaining degradation prediction data of the coating in the environment, wherein the result is shown in Table 2, the prediction result is more accurate, and the result is shown in figure 3 compared with the experimental result.
Step five: and calculating process reliability evaluation indexes. The failure threshold value of the bonding strength of the coating is 39MPa, new environmental stress is brought into an environmental effect model, and degradation data of the coating under the new environmental stress can be obtained. Based on a stress-intensity interference model, defining stress as a failure threshold value of coating bonding strength, wherein the strength is a numerical value of the degradation of the coating bonding strength along with time, and when the degradation value of the coating bonding strength is greater than or equal to the failure threshold value of the bonding strength, a product coating does not generate blistering and peeling and can realize the function of protecting a product substrate, so that the probability that the degradation value of the coating bonding strength at a certain moment under different environments is greater than or equal to the failure threshold value of the bonding strength is used as an index I of a surface modification process reliability evaluation method based on an environmental effect, and the index I is as follows:
I＝P(Ci> F) and Ci＝C1-X(t) (2)
Wherein C isiIs the bond strength at which the coating degrades, X (t) is the amount of degradation of the bond strength of the coating as a function of time t, C1Is the initial value of the coating bond strength and F is the failure threshold of the coating bond strength.
When the coating begins to degrade, the bonding strength of the coating gradually decreases under the action of environmental stress and time, and the degradation of the bonding strength of the coating is strictly regular, and the degradation increment X (t + delta t) -X (t) of the bonding strength is shown in FIG. 4. Through the random simulation of the dynamic environment of the area, a degradation curve of the bonding strength of the coating can be calculated based on an environmental effect model, as shown in fig. 5, since the failure threshold of the bonding strength of the coating is 39MPa, the failure time of the coating under different environmental stresses obeys gamma distribution as follows:
T～Ga(X；αΔt，β) (3)
where α Δ t is a shape parameter and α Δ t > 0, β is a scale parameter and β > 0, Ga (-) denotes a Gamma distribution, the distribution density function of the coating failure time is:
Figure BDA0001270137690000112
substituting the above formula into (1) can obtain a calculation formula of the process reliability evaluation index, which is as follows:
Figure BDA0001270137690000121
solving equation (5) by using Matlab, wherein parameters are estimated by using a maximum likelihood estimation method, and the calculation result is shown in table 3:
TABLE 3 parameter estimation
Figure BDA0001270137690000122
By substituting the parameters and the prediction data into the calculation formula of the evaluation index, a curve that the characteristic given to the surface of the product by the process is gradually degraded along with time can be obtained, and the curve is shown in fig. 6. Through the curve, the adaptive capacity of the surface modification process in the working environment is continuously reduced under the action of environmental stress, and when the degradation time reaches 150 experimental steps, the capacity of the surface modification process endowing the product with the surface characteristic capable of resisting the external environment corrosion is almost zero.
Wherein:
the mechanism in the first step is that under the action of a seawater environment, the surface layer or the internal structure of the coating can generate corrosion reaction, the bonding strength is gradually reduced due to the gradual increase of corrosion products, and the foaming and the stripping occur until the failure threshold value under the environment is lower.
The neural network in the third step is a feedforward neural network comprising an input layer, an output layer and a hidden layer, wherein the hidden layer comprises 10 neurons, the excitation function of the hidden layer adopts a Sigmond function, and the optimization algorithm adopts a Levenberg-Marquardt back prediction algorithm. In the training data, the sample of the input layer is a vector containing six dimensions, and the output layer is a vector containing one dimension.

Claims (5)

1. A surface modification process reliability evaluation method based on environmental effect is characterized in that: the method comprises the following specific steps:
the method comprises the following steps: analyzing the integrity characteristics of the key surface and the stress of the sensitive environment; analyzing a typical failure mode of a product in a natural environment, and determining a key surface integrity characteristic C ═ C of the product according to a failure mechanism1，C2，C3，…，CN]Wherein N represents the class of critical surface integrity features; determining the sensitive environmental stress S ═ S based on the sensitivity of the environmental stress to the degradation process of the integrity characteristics of the key surface1，S2，S3，…，SL]Wherein L represents the kind of sensitive environmental stress;
step two: critical surface integrity feature degradation experiments; detecting the degradation process of the product with the modified surface in the natural environment, and recording the degradation data of the product; the specific experimental method comprises the steps of firstly detecting the integrity characteristics of each key surface when the product is not degraded, and then measuring the characteristics C once every degradation time delta t until the characteristics are degraded to a failure threshold value; after the experiment is finished, simultaneously monitoring the stress of the sensitive environment in real time and recording data Cij，CijJ-th detection data representing the integrity characteristics of the ith type of key surface;
step three: establishing a degradation prediction model; and constructing a data vector by using the product degradation data and the environment data, wherein each sample vector of the neural network input layer is in the form of:
X＝[S1j，S2j，S3j，…，SLj，C1j，C2j，C3j，…，CNj]
wherein: x represents a vector of samples and X represents,
[S1j，S2j，S3j，…，SLj，C1j，C2j，C3j，…，CNj]representing a sample vector formed by the jth monitoring value of the L-class environmental stress and the jth monitoring value of the N-class key surface integrity characteristic; each sample vector of the output layer is Y ═ C1j，C2j，C3j，…，CNj]C of theijJ-th detection data representing the integrity characteristics of the ith type of key surface; establishing a degradation prediction model based on the surface integrity characteristics of the environmental effect by combining a neural network algorithm, and training a neural network until the precision meets the requirement to obtain the prediction model;
step four: predicting the degradation of the integrity characteristics of the key surface in a dynamic environment; bringing the new sensitive environment stress data and the degradation initial value of the key surface integrity characteristic into a degradation prediction model, and calculating the degradation prediction data of the surface integrity characteristic in the environment;
step five: calculating an evaluation index; combining a stress-intensity interference model, taking a failure threshold value of surface integrity characteristics as intensity, taking a detection value of the surface integrity characteristics as stress, calculating the probability that a key surface integrity characteristic value is greater than the failure threshold value under the action of a dynamic environment effect, comparing all key surface integrity characteristics and meeting the specified requirements, taking the minimum value as an evaluation index, and realizing the evaluation of the surface modification process based on the environment effect, wherein the calculation mode of the evaluation index I is as follows:
I＝minP(Cij＞Fi) And Cij＝Ci1-X(t) (1)
Wherein I represents the process reliability evaluation index, min represents the minimum value, FiFailure threshold, C, representing the integrity feature of the i-th class of critical surfacesi1An initial value representing the bond strength of the coating, x (t) representing the amount of degradation of the key surface integrity feature over time;
through the steps, the degradation process of the key surface integrity feature in the dynamic environment can be accurately predicted, the probability that the key surface integrity feature is larger than the degradation threshold value at a certain moment in the dynamic environment is calculated, the capability of the process for resisting the environmental stress can be evaluated, the reliability evaluation of the process is realized, and the optimization of the process flow can be helped.
2. The method for evaluating the reliability of the surface modification process based on the environmental effect as claimed in claim 1, wherein: the "critical surface integrity characteristics" referred to in step one refer to, but are not limited to, hardness, roughness, and bond strength.
3. The method for evaluating the reliability of the surface modification process based on the environmental effect as claimed in claim 1, wherein: the "sensitive environmental stress" in step one refers to, but is not limited to, the temperature stress S in the seawater environmentTpH value SPDissolved oxygen SDSalinity SSAnd oxidation-reduction potential SOPR。
4. The method for evaluating the reliability of the surface modification process based on the environmental effect as claimed in claim 1, wherein: in the third step, the method of building a degradation prediction model of surface integrity characteristics based on environmental effects in combination with a neural network algorithm, training a neural network until the precision meets the requirements, and obtaining a prediction model comprises the following steps: changing X to [ S ]1j，S2j，S3j，…，SLj，C1j，C2j，C3j，…，CNj]Substituting Y ═ C into the input layer of the neural network algorithm1j，C2j，C3j，…，CNj]Substituting into the output layer of the neural network algorithm, and setting the neural network structure and the iteration times, precision and learning rate of the algorithm according to specific conditions.
5. The method for evaluating the reliability of the surface modification process based on the environmental effect as claimed in claim 1, wherein: the method for "substituting the new sensitive environment stress data and the initial value of the degradation of the key surface integrity feature into the degradation prediction model to calculate the degradation prediction data of the surface integrity feature in the environment" in the fourth step is as follows: substituting the new sensitive environmental stress data and the degradation initial value of the key surface integrity characteristic into the degradation prediction model as the input layer of the model, sequentially calculating the degradation result, and then continuously iterating the degradation result and the environmental stress data to obtain the degradation process data of the key surface integrity characteristic.
CN201710244055.0A 2017-04-14 2017-04-14 Surface modification process reliability evaluation method based on environmental effect Active CN107169165B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710244055.0A CN107169165B (en) 2017-04-14 2017-04-14 Surface modification process reliability evaluation method based on environmental effect

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710244055.0A CN107169165B (en) 2017-04-14 2017-04-14 Surface modification process reliability evaluation method based on environmental effect

Publications (2)

Publication Number Publication Date
CN107169165A CN107169165A (en) 2017-09-15
CN107169165B true CN107169165B (en) 2020-07-07

Family

ID=59849931

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710244055.0A Active CN107169165B (en) 2017-04-14 2017-04-14 Surface modification process reliability evaluation method based on environmental effect

Country Status (1)

Country Link
CN (1) CN107169165B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108229761B (en) * 2018-03-16 2020-08-21 中国电子科技集团公司第三十六研究所 Comprehensive optimization method for environmental stress screening test and prediction maintenance
CN108764609A (en) * 2018-04-10 2018-11-06 北京航空航天大学 A kind of inherent reliability appraisal procedure based on multi-source manufacturing process information

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103955568A (en) * 2014-04-17 2014-07-30 北京航空航天大学 Physics-of-failure-based MOS (metal oxide semiconductor) device reliability simulation evaluation method
CN104794282A (en) * 2015-04-22 2015-07-22 北京航空航天大学 Electromagnetic compatibility reliability evaluation method for avionic device power supply module
CN106529090A (en) * 2016-12-12 2017-03-22 中国航天标准化研究所 Evaluation method of reliability of aerospace electronic product

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103955568A (en) * 2014-04-17 2014-07-30 北京航空航天大学 Physics-of-failure-based MOS (metal oxide semiconductor) device reliability simulation evaluation method
CN104794282A (en) * 2015-04-22 2015-07-22 北京航空航天大学 Electromagnetic compatibility reliability evaluation method for avionic device power supply module
CN106529090A (en) * 2016-12-12 2017-03-22 中国航天标准化研究所 Evaluation method of reliability of aerospace electronic product

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
Reliability Improvement of Hemp Based Bio-composite by Surface Modification;Jeong Tak Oh等;《Fibers and Polymers》;20120801;第13卷(第6期);第735-739页 *
空间用SiC反射镜表面改性的性能和可靠性评估;申振峰等;《光子学报》;20090930;第38卷(第9期);第2353-2358页 *
零部件热处理与表面改性新技术应用;张先鸣;《现代零部件》;20130501(第5期);第49-51页 *

Also Published As

Publication number Publication date
CN107169165A (en) 2017-09-15

Similar Documents

Publication Publication Date Title
Lasheras et al. The use of design of experiments to improve a neural network model in order to predict the thickness of the chromium layer in a hard chromium plating process
Sadowski Non-destructive investigation of corrosion current density in steel reinforced concrete by artificial neural networks
Parthiban et al. Neural network analysis for corrosion of steel in concrete
Zadeh Shirazi et al. A hybrid intelligent model combining ANN and imperialist competitive algorithm for prediction of corrosion rate in 3C steel under seawater environment
CN107169165B (en) Surface modification process reliability evaluation method based on environmental effect
CN109409271B (en) Ferromagnetic material hardness prediction algorithm based on BP neural network improved algorithm
CN102880908A (en) Method for calculating remanufactured part environmental loss based on back propagation (BP) neural network
CN111832703B (en) Irregular sampling dynamic sequence modeling method for process manufacturing industry
CN115186590A (en) Method for predicting residual life of pipeline corrosion
CN115982141A (en) Characteristic optimization method for time series data prediction
CN115640744A (en) Method for predicting corrosion rate outside oil field gathering and transportation pipeline
CN110705131A (en) Mechanical component service life prediction method based on high cycle fatigue of machined surface layer
Kumar et al. Use of artificial neural network models to predict coated component life from short-term electrochemical impedance spectroscopy measurements
Domzalicki et al. Large scale corrosion tests
Ma et al. Application of machine learning in material corrosion research
Mahmoudi et al. A novel method to determine material properties and residual stresses simultaneously using spherical indentation
Ahmad et al. Modeling of surface roughness in turning operation using extreme learning machine
Afshar et al. Simulation of corrosion protection methods in reinforced concrete by artificial neural networks and fuzzy logic
Vagaská et al. The application of neural networks to control technological process
Colorado-Garrido et al. Artificial neural networks for electrochemical impedance spectroscopy sour corrosion predictions of nano-modified microalloyed steels
Kiselev et al. Analysis of corrosion behavior of steel 3 in chloride solutions by using neural networks
Fan et al. Application of artificial neural network in prediction of bond property between corroded reinforcement and concrete
Lajevardi et al. Prediction of time to failure in stress corrosion cracking of 304 stainless steel in aqueous chloride solution by artificial neural network
Liu et al. The Prediction of Steel Bar Corrosion Based on BP Neural Networks or Multivariable Gray Models
Qu et al. Parameter identification method of large macro-micro coupled constitutive models based on identifiability analysis

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant