阅读说明：本技术 医用镁基材料复合生物涂层降解速率可控的方法 (Method for controlling degradation rate of medical magnesium-based material composite biological coating ) 是由 熊缨 朱涛 杨杰 沈永水 何留永 于 2020-05-26 设计创作，主要内容包括：医用镁基材料复合生物涂层降解速率可控的方法,通过改变6个影响降解速率的工艺参数来制备不同降解速率的医用镁基材料复合生物涂层,6个工艺参数为激光能量、喷丸温度、激光喷丸次数、电流密度、处理时间和电解液浓度,以上述6个工艺参数为输入层,降解速率为输出层,使用遗传算法优化的BP神经网络进行网络训练,得到一个误差较小的BP神经网络预测模型。本发明具有良好的智能特性,大大简化了降解速率的预测与控制过程,节省了人力、物力与财力。有效地提高了医用镁合金植入材料的耐腐蚀性能和机械性能,为医用镁合金植入材料的广泛使用提供了可能。(A medical magnesium-based material composite biological coating degradation rate controllable method is characterized in that medical magnesium-based material composite biological coatings with different degradation rates are prepared by changing 6 process parameters influencing the degradation rates, the 6 process parameters comprise laser energy, shot blasting temperature, laser shot blasting times, current density, processing time and electrolyte concentration, the 6 process parameters are used as input layers, the degradation rates are used as output layers, and a BP neural network optimized by a genetic algorithm is used for network training to obtain a BP neural network prediction model with a small error. The invention has good intelligent characteristic, greatly simplifies the prediction and control process of the degradation rate, and saves manpower, material resources and financial resources. Effectively improves the corrosion resistance and the mechanical property of the medical magnesium alloy implant material and provides possibility for the wide use of the medical magnesium alloy implant material.)

1. The method for controlling the degradation rate of the medical magnesium-based material composite biological coating is characterized by comprising the following steps:

(1) acquiring degradation rate of N groups of LSP/MAO composite biological coatings and 6 process parameters influencing the degradation rate, wherein the 6 process parameters are as follows: laser energy, shot blasting temperature, laser shot blasting times, current density, processing time and electrolyte concentration, wherein N is more than or equal to 50;

(2) establishing a BP neural network, wherein the BP neural network comprises an input layer, a hidden layer and an output layer; the number of hidden layer nodes is determined according to simulation training and test results;

(3) optimizing the established BP neural network by adopting a genetic algorithm;

(4) training and testing the optimized BP neural network; taking the N groups of parameter values obtained in the step 1 as basic training samples, wherein the parameter values of laser energy, shot blasting temperature, laser shot blasting times, current density, processing time and electrolyte concentration are taken as input layer data, the degradation rate corresponding to the input layer data is taken as output layer data, and the weight and the threshold of the network are processed, so that the weight and the threshold of the network are adjusted along the negative gradient direction of network error change, the network error reaches the minimum value or the minimum value, and a BP neural network model with extremely small error rate is obtained;

(5) predicting the degradation rate of the LSP/MAO composite biological coating by using the obtained BP neural network model;

(6) controlling the degradation rate of the LSP/MAO composite biological coating by using the obtained BP neural network model; setting a target degradation rate, and judging whether the error between the target degradation rate and the degradation rate predicted by the BP neural network model is within an error threshold value:

if so, preparing the LSP/MAO composite biological coating according to the preset 6 process parameter values;

if not, updating the preset 6 process parameter values, so that the error between the degradation rate predicted by the BP neural network model and the target degradation rate is within an error threshold value.

2. The method for controlling the degradation rate of the medical magnesium-based material composite biological coating according to claim 1, wherein the method comprises the following steps: the process of optimizing by using the genetic algorithm BP neural network in the step 3 comprises the following steps:

a. firstly, determining and generating an initial population, and coding the population;

b. performing fitness analysis on the population, directly outputting optimal individuals and parameters according with an optimization principle, and ending, wherein at the moment, an initial weight and a threshold value of the BP neural network optimized through a genetic algorithm are obtained; otherwise, carrying out the next step;

c. selecting individuals according to the fitness, and reserving the individuals with high fitness;

d. carrying out cross mutation on the selected population, wherein a cross operator acts on the individuals of the whole population to form a new generation;

e. carrying out structural variation adjustment on individuals in the whole group by using a variation operator to generate new individuals;

f. and (c) all the individuals after the selection and cross mutation process become a next generation group, and repeating the step b.

3. The method for controlling the degradation rate of the medical magnesium-based material composite biological coating according to claim 1, wherein the method comprises the following steps: the preparation method of the LSP/MAO composite biological coating comprises the following steps:

(1.1) preparation of LSP coating: adopting the parameter values of the laser energy, the shot blasting temperature and the laser shot blasting times determined in the step 6, and adopting a laser to carry out laser shock on the surface of the magnesium-based material to prepare an LSP coating sample on the surface of the magnesium-based material;

(1.2) preparation of LSP/MAO composite biological coating: taking the LSP coating sample prepared in the step (1.1) as a basic sample, and selecting sodium silicate, sodium fluoride, potassium hexafluorotitanate, hydroxyapatite and ethylene glycol as electrolyte components, wherein Na is₂SiO₃·9H₂O：12g/L，NaF：5g/L，K₂TiF₆: 2g/L, HA nanoparticles (20 nm): 3g/L, ethylene glycol: 10 ml/L; adjusting the pH value of the electrolyte to 12 by using NaOH; preparing an LSP/MAO composite biological coating on the surface of the LSP coating sample by adopting the parameter values of the current density, the processing time and the electrolyte concentration determined in the step 6;

(1.3) the outer layer of the LSP/MAO composite biological coating is a MAO layer, and the MAO layer is an important part for preventing corrosion of the composite biological coating, so that the corrosion resistance of the composite biological coating can be improved, and the fixation of a medical implant to bone can be enhanced; the LSP coating is an inner layer of the composite biological coating and mainly has the functions of refining crystal grains on the surface of the magnesium-based material and compressing a residual stress field, so that the mechanical properties of the medical magnesium-based material, such as fatigue, corrosion cracking, wear resistance and the like, are improved;

(1.4) in view of the (1.3), the anticorrosion capability and the mechanical property of the inner layer of the composite biological coating can be adjusted by changing the LSP related process parameters, and different process parameters can be set to prepare the inner layer of the composite biological coating with different properties;

(1.5) in view of the (1.3), the anticorrosion capability of the outer layer of the composite biological coating can be adjusted by changing MAO related process parameters, and different process parameters can be set to prepare the outer layer of the composite biological coating with different properties;

(1.6) three factors that influence the degradation rate of LSP coatings are: laser energy, peening temperature, and laser peening times, and three factors that affect the degradation rate of the MAO coating are: current density, treatment time, electrolyte concentration; taking the effects and the technological properties of the six factors into consideration, and preparing the LSP/MAO composite biological coating with different corrosion resistance by jointly changing the six factors; and performing an in-vitro soaking test of an SBF solution on the prepared LSP/MAO composite biological coating, and evaluating the corrosion resistance of the LSP/MAO composite biological coating in the SBF by adopting a common corrosion rate characterization means of a magnesium-based material, a weight loss and hydrogen evolution method and an electrochemical test method, namely an electrochemical impedance spectrum and a potentiodynamic polarization curve to obtain a degradation rate parameter value of the LSP/MAO composite biological coating.

Technical Field

The invention relates to the technical field of medical magnesium-based material composite biological coatings, in particular to a method for controlling the degradation rate of a medical magnesium-based material composite biological coating.

Background

Magnesium, as an important element necessary for the synthesis and metabolism of human substances, has good biocompatibility and mechanical properties, and has density and mechanical properties close to those of human bones, so that the magnesium attracts the attention of medical workers early in the 20 th century. The unique in vivo degradation characteristic can effectively avoid secondary operation brought by the traditional implant material, so the medical implant material is regarded as the most promising medical implant material. However, the medical biological magnesium alloy has poor corrosion resistance, and clinical researches find that the mechanical property of the magnesium alloy implant material is reduced in a short time due to the excessively fast in vivo corrosion rate, so that the biomechanical support necessary for healing of the diseased part and the medium conduction depending on tissue growth are difficult to maintain, and simultaneously, along with the generation of hydrogen, bubbles are rapidly accumulated under the skin, and the medical biological magnesium alloy implant material is harmful to the health of a human body.

The corrosion resistance problem limits the wide application of magnesium-based materials as medical implant materials for a long time, and how to control the degradation rate of the magnesium-based materials is also a key point. In order to improve the corrosion resistance of magnesium-based materials, researchers have conducted a great deal of research into the corrosion behavior of magnesium-based materials, and many methods for improving the corrosion resistance of magnesium alloys, such as alloying, coating techniques, and processing techniques, have been proposed. The coating technology has obvious advantages, and various magnesium alloy surface modification technologies such as laser shot blasting (LSP) and micro-arc oxidation (MAO) are made. LSP is an alternative non-contact surface treatment that uses laser shock waves, high power and short pulses to impact the target surface to improve the mechanical properties of the metallic material, such as fatigue, corrosion cracking and wear resistance, and to improve the bond between the coating and the substrate. MAO is a novel surface modification technology in recent years, and the principle is that on the basis of common anodic oxidation, a common anodic oxidation method takes a high-voltage spark power generation area as a working area under a higher working voltage, and a ceramic film layer is directly grown in situ on the surface of a non-ferrous metal matrix (magnesium, aluminum, titanium and other metals and alloys thereof). The composite biological coating prepared by combining MAO technology and LSP technology combines the advantages of MAO technology and LSP technology, and has better corrosion resistance.

The magnesium-based medical implant material must ensure absolute corrosion resistance after being implanted into a human body, maintain enough strength, and degrade at a controllable and predictable rate after being used, so as to be absorbed or metabolized by the human body. The corrosion resistance of the medical magnesium-based implant material can be improved after surface modification, but the degradation rate of the medical magnesium-based implant material cannot be predicted. How to ensure that the medical magnesium-based implant material can not be degraded in advance after being implanted into a human body is a key point for wide use of the medical magnesium-based implant material, so that the controllable and predictable degradation rate of the medical magnesium-based implant material must be realized. The BP artificial neural network is a parallel distributed system, adopts a mechanism completely different from the traditional artificial intelligence and information processing technology, overcomes the defects of the traditional artificial intelligence based on logic symbols in the aspects of processing intuition and unstructured information, and has the characteristics of self-adaption, self-organization and real-time learning. The research work of the BP artificial neural network is continuous and deep, great progress has been made, the BP artificial neural network successfully solves many practical problems which are difficult to solve by modern computers in the fields of pattern recognition, intelligent robots, automatic control, prediction estimation, biology, medicine, economy and the like, and the BP artificial neural network shows good intelligent characteristics. Therefore, by combining the magnesium alloy surface modification technology and the BP artificial neural network technology, the method for predicting the controllable degradation rate of the medical magnesium-based implant material composite biological coating after surface modification by the LSP technology and the MAO technology is obtained, and the method has extremely important significance for the development and application of the medical magnesium-based implant material.

Disclosure of Invention

In order to overcome the problems, the invention provides a method for controlling the degradation rate of a medical magnesium-based material composite biological coating.

The technical scheme adopted by the invention is as follows: the method for controlling the degradation rate of the medical magnesium-based material composite biological coating comprises the following steps:

(1) acquiring degradation rate of N groups of LSP/MAO composite biological coatings and 6 process parameters influencing the degradation rate, wherein the 6 process parameters are as follows: laser energy, shot blasting temperature, laser shot blasting times, current density, processing time and electrolyte concentration, wherein N is more than or equal to 50;

(2) establishing a BP neural network, wherein the BP neural network comprises an input layer, a hidden layer and an output layer; the number of hidden layer nodes is determined according to simulation training and test results;

(3) optimizing the established BP neural network by adopting a genetic algorithm;

(4) training and testing the optimized BP neural network; taking the N groups of parameter values obtained in the step 1 as basic training samples, wherein the parameter values of laser energy, shot blasting temperature, laser shot blasting times, current density, processing time and electrolyte concentration are taken as input layer data, the degradation rate corresponding to the input layer data is taken as output layer data, and the weight and the threshold of the network are processed, so that the weight and the threshold of the network are adjusted along the negative gradient direction of network error change, the network error reaches the minimum value or the minimum value, and a BP neural network model with extremely small error rate is obtained;

(5) predicting the degradation rate of the LSP/MAO composite biological coating by using the obtained BP neural network model;

(6) controlling the degradation rate of the LSP/MAO composite biological coating by using the obtained BP neural network model; setting a target degradation rate, and judging whether the error between the target degradation rate and the degradation rate predicted by the BP neural network model is within an error threshold value:

if so, preparing the LSP/MAO composite biological coating according to the preset 6 process parameter values;

if not, updating the preset 6 process parameter values, so that the error between the degradation rate predicted by the BP neural network model and the target degradation rate is within an error threshold value.

Further, the process of optimizing by using the genetic algorithm BP neural network in step 3 includes the following steps:

a. firstly, determining and generating an initial population, and coding the population;

b. performing fitness analysis on the population, directly outputting optimal individuals and parameters according with an optimization principle, and ending, wherein at the moment, an initial weight and a threshold value of the BP neural network optimized through a genetic algorithm are obtained; otherwise, carrying out the next step;

c. selecting individuals according to the fitness, and reserving the individuals with high fitness;

d. carrying out cross mutation on the selected population, wherein a cross operator acts on the individuals of the whole population to form a new generation;

e. carrying out structural variation adjustment on individuals in the whole group by using a variation operator to generate new individuals;

f. and (c) all the individuals after the selection and cross mutation process become a next generation group, and repeating the step b.

Further, the preparation of the LSP/MAO composite biological coating comprises the following steps:

(1.1) preparation of LSP coating: adopting the parameter values of the laser energy, the shot blasting temperature and the laser shot blasting times determined in the step 6, and adopting a laser to carry out laser shock on the surface of the magnesium-based material to prepare an LSP coating sample on the surface of the magnesium-based material;

(1.2) preparation of LSP/MAO composite biological coating: taking the LSP coating sample prepared in the step (1.1) as a basic sample, and selecting sodium silicate, sodium fluoride, potassium hexafluorotitanate, hydroxyapatite and ethylene glycol as electrolyte components, wherein Na is₂SiO₃·9H₂O：12g/L，NaF：5g/L，K₂TiF₆: 2g/L, HA nanoparticles (20 nm): 3g/L, ethylene glycol: 10 ml/L; adjusting the pH value of the electrolyte to 12 by using NaOH; preparing an LSP/MAO composite biological coating on the surface of the LSP coating sample by adopting the parameter values of the current density, the processing time and the electrolyte concentration determined in the step 6;

(1.3) the outer layer of the LSP/MAO composite biological coating is a MAO layer, and the MAO layer is an important part for preventing corrosion of the composite biological coating, so that the corrosion resistance of the composite biological coating can be improved, and the fixation of a medical implant to bone can be enhanced; the LSP coating is an inner layer of the composite biological coating and mainly has the functions of refining crystal grains on the surface of the magnesium-based material and compressing a residual stress field, so that the mechanical properties of the medical magnesium-based material, such as fatigue, corrosion cracking, wear resistance and the like, are improved;

(1.4) in view of the (1.3), the anticorrosion capability and the mechanical property of the inner layer of the composite biological coating can be adjusted by changing the LSP related process parameters, and different process parameters can be set to prepare the inner layer of the composite biological coating with different properties;

(1.5) in view of the (1.3), the anticorrosion capability of the outer layer of the composite biological coating can be adjusted by changing MAO related process parameters, and different process parameters can be set to prepare the outer layer of the composite biological coating with different properties;

(1.6) three factors that influence the degradation rate of LSP coatings are: laser energy, shot-peening temperature, and laser shot-peening times, and three factors affecting the degradation rate of the MAO coating are: current density, treatment time, electrolyte concentration; taking the effects and the technological properties of the six factors into consideration, and preparing the LSP/MAO composite biological coating with different corrosion resistance by jointly changing the six factors; and performing an in-vitro soaking test of an SBF solution on the prepared LSP/MAO composite biological coating, and evaluating the corrosion resistance of the LSP/MAO composite biological coating in the SBF by adopting a common corrosion rate characterization means of a magnesium-based material, a weight loss and hydrogen evolution method and an electrochemical test method, namely an electrochemical impedance spectrum and a potentiodynamic polarization curve to obtain a degradation rate parameter value of the LSP/MAO composite biological coating.

The invention has the beneficial effects that: (1) the composite biological coating is prepared on the magnesium-based material by combining the LSP and MAO surface modification technologies, so that the corrosion resistance and the mechanical property of the medical magnesium alloy implant material are effectively improved, and the possibility is provided for the wide application of the medical magnesium alloy implant material.

(2) Testing and training a large amount of test data pairs by using a BP neural network model improved by a genetic algorithm to obtain a prediction model with a very small error; the prediction model has good intelligent characteristics, greatly simplifies the prediction and control process of the degradation rate, and saves manpower, material resources and financial resources.

(3) The degradation rate of the composite biological coating prepared under any group of six process parameters related to LSP and MAO can be predicted and controlled by the prediction model, the analysis and prediction of degradation data obtained by an in vitro soaking test are simply and effectively realized, and a certain foundation is laid for the large-scale popularization and use of medical magnesium alloy implant materials.

Drawings

FIG. 1 is a schematic diagram of a BP neural network of the present invention.

FIG. 2 is a schematic diagram of the genetic algorithm optimized BP neural network of the present invention.

FIG. 3 is a cross-sectional Scanning (SEM) schematic of a sample of LSP/MAO composite biocoating prepared under one parameter condition of the present invention.

FIG. 4 is a schematic representation of texture XRD of the sample surface before and after treatment of LSP prepared from one of the parameters of the present invention.

FIG. 5 is a schematic XRD of MAO coatings and LSP/MAO composite biocoatings prepared under one parameter of the present invention.

FIG. 6 is a graphical representation of the zeta potential polarization curve of the degradation in SBF of a coated sample prepared with one of the parameters of the present invention.

Detailed Description

The invention will be further described with reference to specific examples, but the scope of the invention is not limited thereto:

referring to the attached drawings, (1) acquiring degradation rate of N groups of LSP/MAO composite biological coating and 6 process parameters having influence on the degradation rate, wherein the 6 process parameters are as follows: laser energy, shot blasting temperature, laser shot blasting times, current density, processing time and electrolyte concentration, wherein N is more than or equal to 50;

(2) establishing a BP neural network, wherein the BP neural network comprises an input layer, a hidden layer and an output layer; the number of hidden layer nodes is determined according to simulation training and actual test results;

(3) optimizing the established BP neural network by adopting a genetic algorithm;

the process of optimizing by adopting a genetic algorithm BP neural network comprises the following steps:

a. firstly, determining and generating an initial population, and coding the population;

b. performing fitness analysis on the population, directly outputting optimal individuals and parameters according with an optimization principle, and ending, wherein at the moment, an initial weight and a threshold value of the BP neural network optimized through a genetic algorithm are obtained; otherwise, carrying out the next step;

c. selecting individuals according to the fitness, and reserving the individuals with high fitness;

d. carrying out cross mutation on the selected population, wherein a cross operator acts on the individuals of the whole population to form a new generation;

e. carrying out structural variation adjustment on individuals in the whole group by using a variation operator to generate new individuals;

f. and (c) all the individuals after the selection and cross mutation process become a next generation group, and repeating the step b.

(4) Training and testing the optimized BP neural network; taking the N groups of data values obtained in the step 1 as basic training samples, wherein the parameter values of laser energy, shot blasting temperature, laser shot blasting times, current density, processing time and electrolyte concentration are taken as input layer data, the degradation rate corresponding to the input layer data is taken as output layer data, and the weight and the threshold of the network are processed, so that the weight and the threshold of the network are adjusted along the negative gradient direction of network error change, the network error reaches the minimum value or the minimum value, and a BP neural network model with extremely small error rate is obtained;

(5) predicting the degradation rate of the LSP/MAO composite biological coating by using the obtained BP neural network model;

(6) controlling the degradation rate of the LSP/MAO composite biological coating by using the obtained BP neural network model; setting a target degradation rate, simultaneously presetting 6 process parameter values, predicting the degradation rate by using the obtained BP neural network model, and judging whether the error between the target degradation rate and the degradation rate predicted by the BP neural network model is within an error threshold value:

if so, preparing the LSP/MAO composite biological coating according to the preset 6 process parameter values;

if not, updating the preset 6 process parameter values, so that the error between the degradation rate predicted by the BP neural network model and the target degradation rate is within an error threshold value.

The preparation method of the LSP/MAO composite biological coating comprises the following steps:

(1.1) preparation of LSP coating: adopting the parameter values of the laser energy, the shot blasting temperature and the laser shot blasting times determined in the step 6, and adopting a laser to carry out laser shock on the surface of the magnesium-based material to prepare an LSP coating sample on the surface of the magnesium-based material;

(1.2) preparation of LSP/MAO composite biological coating: taking the LSP coating sample prepared in the step (1.1) as a basic sample; sodium silicate, sodium fluoride, potassium hexafluorotitanate, hydroxyapatite and ethylene glycol are selected as electrolyte components, wherein Na is₂SiO₃·9H₂O：12g/L，NaF：5g/L，K₂TiF₆: 2g/L, HA nanoparticles (20 nm): 3g/L, ethylene glycol: 10 ml/L; adjusting the pH value of the electrolyte to 12 by using NaOH; preparing an LSP/MAO composite biological coating on the surface of the LSP coating sample by adopting the parameter values of the current density, the processing time and the electrolyte concentration determined in the step 6;

(1.3) the outer layer of the LSP/MAO composite biological coating is a MAO layer, and the MAO layer is an important part for preventing corrosion of the composite biological coating, so that the corrosion resistance of the composite biological coating can be improved, and the fixation of a medical implant to bone can be enhanced; the LSP coating is an inner layer of the composite biological coating and mainly has the functions of refining crystal grains on the surface of the magnesium-based material and compressing a residual stress field, so that the mechanical properties of the medical magnesium-based material, such as fatigue, corrosion cracking, wear resistance and the like, are improved;

(1.4) in view of the (1.3), the anticorrosion capability and the mechanical property of the inner layer of the composite biological coating can be adjusted by changing the LSP related process parameters, and different process parameters can be set to prepare the inner layer of the composite biological coating with different properties;

(1.5) in view of the (1.3), the anticorrosion capability of the outer layer of the composite biological coating can be adjusted by changing MAO related process parameters, and different process parameters can be set to prepare the outer layer of the composite biological coating with different properties;

(1.6) the three most important factors affecting the degradation rate of LSP coatings are: laser energy, peening temperature, and laser peening times, while the three factors that affect MAO coating degradation rate are the most important: current density, treatment time, electrolyte concentration; taking the effects and the technological properties of the six factors into consideration, and preparing the LSP/MAO composite biological coating with different corrosion resistance by jointly changing the six factors; and performing an in-vitro soaking test of an SBF solution on the prepared LSP/MAO composite biological coating, and evaluating the corrosion resistance of the LSP/MAO composite biological coating in the SBF by adopting a common corrosion rate characterization means of a magnesium-based material, a weight loss and hydrogen evolution method and an electrochemical test method, namely an electrochemical impedance spectrum and a potentiodynamic polarization curve to obtain a degradation rate parameter value of the LSP/MAO composite biological coating.

The following are specific examples of the present invention:

a60 mm by 20mm by 2mm hot-rolled AZ80 magnesium alloy sheet was selected as a surface-modified substrate, and the substrate was polished with sandpaper to secure a certain surface toughness. Subsequently, the sample was ultrasonically degreased in ethanol for 10 minutes, washed with distilled water, and then naturally dried in the air.

Preparing an LSP coating by using the pretreated magnesium alloy substrate, and carrying out LSP surface modification on the surface of the substrate by using a YAG laser, wherein the YAG laser process parameters are as follows: the laser energy A is 2J, the shot blasting temperature B is 120 ℃, the laser shot blasting times C is 3, the wavelength is 1064nm, the pulse width is 20ns, the spot diameter is 3mm, and the overlapping rate is 50%. Water with a thickness of about 1mm was used as a transparent cover layer and a professional aluminium foil with a thickness of 0.1mm was used as an absorbent cover layer to protect the substrate surface from thermal effects.

Then, MAO surface modification is further carried out on the treated LSP coating to prepare the LSP/MAO composite biological coating. The MAO process used an alkaline silicate solution, electrolyte concentration D as shown in table 1 below, and electrolyte pH 12 adjusted by NaOH solution. The treated LSP coating and the stainless steel container are respectively used as an anode and a cathode, and the MAO process parameters are set as follows: the current density F was a constant current of 10A/dm2, a duty cycle of 37.5%, the LSP coating was treated by the MAO process with a treatment time E of 20 minutes under the above parameters, and the temperature of the electrolyte was maintained at 20-30 ℃ by means of a cooling system. After MAO process treatment, the prepared LSP/MAO composite biological coating was ultrasonically cleaned in distilled water for 10 minutes and naturally dried in air.

TABLE 1

Keeping the other parameters of the LSP and MAO process unchanged, and changing the parameter values of laser energy A, shot blasting temperature B, laser shot blasting times C, electrolyte concentration D, processing time E and current density F to obtain more than 50 LSP/MAO composite biological coatings.

The various LSP/MAO composite biological coatings prepared under the different parameter conditions are placed in SBF solution with the temperature of 36.5 +/-0.5 ℃ for in-vitro soaking test, and the specific composition of the SBF solution is shown in the following table 2. The average degradation rate G of more than 50 LSP/MAO composite biological coatings soaked in vitro is obtained by utilizing common corrosion rate characterization means of magnesium-based materials, namely a weight loss and hydrogen evolution method and an electrochemical test method, namely an electrochemical impedance spectrum and a potentiodynamic polarization curve.

TABLE 2

f. Setting the multiple test parameters, namely laser energy A, shot blasting temperature B, laser shot blasting times C, electrolyte concentration D, processing time E and current density F as input layer parameters, and setting the corresponding multiple average degradation rates G as output layer parameters. The BP artificial neural network optimized by the genetic algorithm shown in FIG. 2 is used for training and testing, the weight and the threshold of the network are continuously adjusted, the training precision is gradually improved, the weight and the threshold of the network are adjusted along the negative gradient direction of the network error change, and the error of a BP artificial neural network prediction model is reduced. The whole training and testing process needs a plurality of times of iterative operation, so that the training error reaches the required minimum value or minimum value.

g. And (3) establishing a prediction model under the test parameters, flexibly adjusting six process parameters of LSP and MAO process treatment, namely laser energy A, shot blasting temperature B, laser shot blasting times C, electrolyte concentration D, treatment time E and current density F, and realizing controllable and predictable average degradation rate G of the LSP/MAO composite biological coating.

The embodiments described in this specification are merely illustrative of implementations of the inventive concept and the scope of the present invention should not be considered limited to the specific forms set forth in the embodiments but rather by the equivalents thereof as may occur to those skilled in the art upon consideration of the present inventive concept.