Femoral fiber-imitating composite material positioner and design method

Abstract

The invention discloses a thighbone-imitating fiber composite material positioner and a design method, and belongs to the technical field of positioners. A thighbone-imitating fiber composite material positioning pipe is lightened by about 40% compared with a traditional metal positioner under the condition of equal rigidity, the influence of the current collection quality is effectively reduced, and the positioning effect of the thighbone-imitating fiber composite material positioning pipe is effectively improved under the condition of equal quality. According to the design method of the thighbone-imitating fiber composite material positioning pipe, based on the mode of combining ABAQUS analogue simulation and a BP neural network, the time cost is greatly reduced, the adaptability of the positioner is improved, the service life of the positioner is prolonged, the maintenance cost is reduced, and along with further expansion of a database in the using process, the positioning accuracy is improved. The time cost is greatly reduced, the adaptability of the positioner is improved, the service life of the positioner is prolonged, the maintenance cost is reduced, and the accuracy of the mapping relation between the structural parameters and the deformation is improved along with further expansion of a database in the using process.

Description

Technical Field

[0001] The invention discloses a femoral imitation fiber composite material positioner and a design method, belonging to the technical field of positioners. Background Art

[0002] With the development of rail transit, the requirements for lightweight, efficient and high-performance materials are getting higher and higher. Carbon fiber composite materials have excellent properties such as light weight, high strength, high stiffness, excellent vibration reduction, fatigue resistance and corrosion resistance. Advanced composite materials, represented by high-performance carbon fiber composite materials, as structural, functional or structural and functional integrated materials, are not only irreplaceable in the construction of national defense strategic weapons, but also will play an extremely important role in the construction of green energy, the development of energy-saving technologies and the promotion of energy diversification.

[0003] Traditional positioners are generally aluminum alloy positioners. The overall mass of the positioner greatly affects the current receiving quality, the fatigue resistance and corrosion resistance are poor, the maintenance cost is high, and it is difficult to determine the optimal size specifications of the positioner required for each route.

[0004] At present, there are a few locators made of composite materials on the market. Their internal support structure is only filled with PMI foam, the internal pore distribution of the structure is unreasonable and it is an open-cell structure. The number of external carbon fiber layers is difficult to determine, and the weight and structure of the locator need to be further optimized. Therefore, how to reasonably apply composite materials to railway locators is a problem that needs to be solved in the current engineering field. Summary of the invention

[0005] In view of the defects of the prior art, the present invention proposes a femoral fiber composite material positioner and design method to solve the problems that the internal support structure of the positioner currently made of composite materials is only filled with PMI foam, the internal pore distribution is unreasonable and it is an open-pore structure, and the number of external carbon fiber layers is difficult to determine.

[0006] The technical solution of the present invention is as follows:

[0007] According to a first aspect of an embodiment of the present invention, there is provided a femoral imitation fiber composite material positioner, comprising a positioning tube, wherein the positioning tube is respectively connected to a positioning connection point and a positioning wire clamp at both ends, the positioning tube comprises a femoral shell, and a femoral imitation support structure and a filling support structure are arranged in the femoral shell cavity, and the bone porosity of the femoral imitation support structure gradually decreases from the positioning wire clamp to the positioning connection point.

[0008] Preferably, the simulated femoral support structure includes a compact bone pore unit area and a cancellous bone pore unit area, the compact bone pore unit area is adjacent to the femoral shell, the pore diameter of the compact bone pore unit area is smaller than the pore diameter of the cancellous bone pore unit area, and the pores of the compact bone pore unit area and the pores of the cancellous bone pore unit area are both closed holes.

[0009] Preferably, the femoral shell is formed by curing and molding a fiber resin layer by heating and pressurizing, and the filling support structure is formed by curing and molding a carbon fiber bundle and a resin by secondary processing.

[0010] According to a second aspect of an embodiment of the present invention, a design method for a femoral imitation fiber composite material positioner is provided, which is applied to a femoral imitation fiber composite material positioner described in the first aspect, comprising:

[0011] Obtaining the design length and the maximum design working load of the positioning tube, and determining the value range of the design parameters of the femoral fiber composite material positioning tube according to the length and the maximum working load of the positioning tube;

[0012] Normalizing the value range of the design parameter of the femoral imitation fiber composite material positioning tube to obtain the value range of the design parameter of the femoral imitation fiber composite material positioning tube after preprocessing;

[0013] Arrange and combine the value ranges of the pre-processed femoral fiber composite material positioning tube design parameters to obtain multiple sets of femoral fiber composite material positioning tube design parameter sets, and bring the multiple sets of femoral fiber composite material positioning tube design parameter sets into the best BP neural network model obtained by training;

[0014] The optimal BP neural network model is used to obtain an optimal femoral imitation fiber composite material positioning tube design parameter group, and a positioning tube model is obtained by modeling according to the optimal femoral imitation fiber composite material positioning tube design parameter group and the positioning tube length;

[0015] A positioning connection point model and a positioning wire clamp model are designed respectively according to the positioning tube model, and the positioning tube model, the positioning connection point model and the positioning wire clamp model are assembled to obtain a locator model.

[0016] Preferably, before obtaining the design length and the maximum design working load of the positioning tube, the method further includes:

[0017] Acquire multiple existing data sets of design parameters of femoral fiber composite positioning tubes and corresponding multiple positioning tube lengths;

[0018] A finite element model of a femoral fiber composite positioning tube is established, and a database of femoral fiber composite positioning tube design parameters and deformation values ​​is constructed by using Python secondary development of ABAQUS simulation according to multiple existing data sets of femoral fiber composite positioning tube design parameters and corresponding multiple positioning tube lengths;

[0019] Preprocessing the design parameters and deformation database of the femoral fiber composite material positioning tube and constructing a training set and a test set;

[0020] A BP neural network model for deformation calculation is constructed, and the BP neural network model is trained and tested using the training set and the test set to obtain an optimal BP neural network model.

[0021] Preferably, the design parameters of the femoral fiber composite positioning tube include: the radius of the femoral shell, the number of carbon fiber layers of the femoral shell, the proportion of the cancellous bone pore unit area and the bone pore reduction coefficient, and the BP neural network model includes: an input layer neural network, a hidden layer neural network and an output layer neural network, wherein:

[0022] The input layer neural network includes: a femoral shell radius input neural unit, a femoral shell carbon fiber layer number input neural unit, a cancellous bone pore unit area ratio input neural unit and a bone pore reduction coefficient input neural unit; the hidden layer neural network includes: 10 hidden neural units and a hidden layer bias; the output layer neural network includes: a deformation output neural unit and an output layer bias.

[0023] Preferably, the using the training set and the test set to train and test the BP neural network model to obtain the best BP neural network model includes:

[0024] The design parameters and deformation of the femoral fiber composite material positioning tube in the training set are weighted and summed with the connection weights of each implicit neural unit, and the value of each implicit neural unit is obtained through the activation function of the input layer, and the value of each implicit neural unit is weighted and summed with the connection weights of the corresponding output neural unit, and the first output deformation is obtained through the activation function of the output layer;

[0025] Subtract the first output deformation from the deformation in the training set to obtain a first error value, and back-propagate the first error value through the BP neural network model to update the connection weights of each hidden neural unit and the connection weights of the output neural unit;

[0026] The updated connection weights of each hidden neural unit and the connection weights of the output neural unit are forward propagated again to obtain a second output deformation, and the second output deformation is subtracted from the deformation in the training set to obtain a second error value, and it is determined whether the second error value is greater than the target error value:

[0027] If yes, the second error value is back-propagated through the BP neural network model again to update the connection weights of each hidden neural unit and the connection weights of the output neural unit through loop iteration until it is less than or equal to the target error value, and then the next step is executed;

[0028] If no, proceed to the next step;

[0029] The connection weights of the current hidden layer neural units and the connection weights of the output neural units are saved, the training of the neural network is completed to obtain the best BP neural network model, and the performance of the best BP neural network model is tested through a test set.

[0030] Preferably, the activation function of the input layer adopts the logsig function, and the activation function of the output layer adopts the sigmoid function.

[0031] Preferably, the step of back-propagating the first error value through a BP neural network model to update the connection weights of each implicit neural unit and the connection weights of the output neural unit includes:

[0032] Multiplying the value obtained by the LM learning algorithm of the first error value by the learning rate to obtain the adjustment value of the connection weight of each hidden neural unit and the adjustment amount of the connection weight of the output neural unit;

[0033] The adjustment value of the connection weight of each hidden neural unit and the adjustment amount of the connection weight of the output neural unit are added to the connection weight of the current hidden neural unit and the connection weight of the output neural unit to obtain the updated connection weight of the hidden neural unit and the connection weight of the output neural unit.

[0034] Preferably, the optimal BP neural network model is used to obtain the optimal femoral fiber composite material positioning tube design parameter group, including:

[0035] Using the optimal BP neural network model to obtain multiple deformation values, and comparing the multiple deformation values ​​to obtain minimum deformation data;

[0036] According to the minimum deformation data, multiple groups of femoral fiber composite material positioning tube design parameter sets are traversed to obtain the corresponding femoral fiber composite material positioning tube design parameter group, and the corresponding femoral fiber composite material positioning tube design parameter group is the optimal femoral fiber composite material positioning tube design parameter group.

[0037] The beneficial effects of the present invention are:

[0038] The present invention provides a femoral fiber composite material positioner and a design method thereof. Under the condition of equal stiffness, the femoral fiber composite material positioning tube is about 40% lighter than a traditional metal positioner, effectively reducing the influence of the flow receiving mass. Under the condition of equal mass, the stiffness and corrosion resistance are improved. The femoral fiber composite material positioning tube is designed based on a combination of ABAQUS simulation and BP neural network, which greatly reduces the time cost, improves the adaptability and service life of the positioner, reduces the maintenance cost, and with the further expansion of the database during use, the time cost is greatly reduced, the adaptability and service life of the positioner are improved, the maintenance cost is reduced, and with the further expansion of the database during use, the accuracy of the mapping relationship between each structural parameter and the deformation amount is improved.

[0039] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 It is a schematic structural diagram of a femoral fiber composite material positioner according to an exemplary embodiment.

[0041] Figure 2 It is a schematic structural diagram showing that the cancellous bone hole unit area of ​​the positioning tube in a femoral fiber composite material positioner accounts for 80% according to an exemplary embodiment.

[0042] Figure 3 It is a schematic structural diagram showing that the cancellous bone hole unit area of ​​the positioning tube in a femoral fiber composite material positioner accounts for 80% according to an exemplary embodiment.

[0043] Figure 4 It is a longitudinal section along A-A' of a positioning tube cancellous bone hole unit area accounting for 80% in a femoral imitation fiber composite material positioner according to an exemplary embodiment.

[0044] Figure 5 It is a schematic structural diagram showing that the cancellous bone hole unit area of ​​the positioning tube in a femoral fiber composite material positioner accounts for 50% according to an exemplary embodiment.

[0045] Figure 6 It is a schematic structural diagram showing that the cancellous bone hole unit area of ​​the positioning tube in a femoral fiber composite material positioner accounts for 50% according to an exemplary embodiment.

[0046] Figure 7 It is a longitudinal section along BB' in which the cancellous bone hole unit area of ​​the positioning tube in a femoral imitation fiber composite material positioner accounts for 50% according to an exemplary embodiment.

[0047] Figure 8It is a schematic structural diagram showing that the cancellous bone hole unit area of ​​the positioning tube in a femoral fiber composite material positioner accounts for 40% according to an exemplary embodiment.

[0048] Fig. 9 It is a schematic structural diagram showing that the cancellous bone hole unit area of ​​the positioning tube in a femoral fiber composite material positioner accounts for 40% according to an exemplary embodiment.

[0049] Fig.10 It is a longitudinal section along CC' of a positioning tube cancellous bone hole unit area accounting for 40% in a femoral imitation fiber composite material positioner according to an exemplary embodiment.

[0050] Fig.11 The present invention is a flow chart showing a design method of a femoral fiber composite material positioner according to an exemplary embodiment.

[0051] Fig.12 It is a topological structure diagram of a BP neural network in a design method of a femoral fiber composite material positioner according to an exemplary embodiment. DETAILED DESCRIPTION

[0052] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0053] In the description of the present invention, it should be noted that the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside", etc. indicate directions or positional relationships based on the directions or positional relationships shown in the accompanying drawings. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operated in a specific direction. Therefore, they cannot be understood as limitations on the present invention.

[0054] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0055] Embodiment 1

[0056] Figure 1A femoral fiber composite material positioner is shown according to an exemplary embodiment, comprising a positioning tube 1, wherein the positioning tube 1 is connected to a positioning connection point 2 and a positioning wire clamp 3 at both ends, such as Figure 2-4 As shown, the positioning tube 1 includes a femoral shell, and a femoral imitation support structure and a filling support structure are arranged in the femoral shell cavity, and the bone porosity of the femoral imitation support structure gradually decreases from the positioning wire clamp 3 to the positioning connection point 2. The porosity at the positioning connection point 2 is the smallest, and the torque it bears is the largest.

[0057] The femoral imitation support structure includes a compact bone pore unit area and a cancellous bone pore unit area. The compact bone pore unit area has a small pore size and a large pore wall thickness; the cancellous bone pore unit area has a large pore size and a small pore wall thickness; the compact bone pore unit area has a high density and a dense structure, has good support and stability, can withstand the body's own gravity and external force, can effectively absorb and disperse external impact and pressure, thereby reducing the impact on the body, and the cancellous bone pore unit area has a relatively small proportion in the body. The compact bone pore unit area is adjacent to the femoral shell, the pore diameter of the compact bone pore unit area is smaller than the pore diameter of the cancellous bone pore unit area, the pores of the compact bone pore unit area and the pores of the cancellous bone pore unit area are both closed pores, and it is difficult for moisture and water to enter, which reduces the cost of maintenance and inspection and prolongs the service life of the support structure. The femoral shell adopts a fiber resin layer that is heated and pressurized to be cured and formed, and the filling support structure is cured and formed by secondary processing of carbon fiber bundles and resin. The different proportions of dense bone pore unit area and cancellous bone pore unit area in the simulated femoral support structure and the bone porosity reduction coefficient θ affect the mass of the positioning tube and the maximum deformation that the positioning tube can withstand. Under the condition of a certain bone porosity reduction coefficient, the proportion of dense bone pore unit area in the simulated femoral support structure increases, the mass of the positioning tube increases, and the maximum deformation that the positioning tube can withstand increases; conversely, the proportion of cancellous bone pore unit area increases, the mass of the positioning tube decreases, and the maximum deformation that the positioning tube can withstand decreases; under a certain proportion of dense bone pore unit area and cancellous bone pore unit area, the bone porosity reduction coefficient θ increases, the density of the positioning tube body area changes greatly, the maximum deformation that can be sustained decreases, but the overall mass decreases; conversely, the density of the positioning tube body area changes less, the maximum deformation that can be sustained increases, but the overall mass increases. Under specified working conditions, determining the optimal proportion of dense bone pore unit area and cancellous bone pore unit area and the optimal bone porosity reduction coefficient θ is of great significance for lightweighting the locator, extending its service life, and reducing costs. Figure 2-4 The positioning tube accounts for 80% of the cancellous bone pore unit area. Figure 5-7 The positioning tube is 50% of the cancellous bone pore unit area, such as Figure 8-10 The cancellous bone pore unit area accounts for 40% of the positioning tube.

[0058] Embodiment 2

[0059] Fig.11 A design method of a femoral fiber composite material positioner according to an exemplary embodiment includes:

[0060] Step 101, obtaining the design length and maximum design working load of the positioning tube, and determining the value range of the design parameters of the femoral fiber composite material positioning tube according to the length and maximum working load of the positioning tube, respectively. The specific steps are as follows:

[0061] Before obtaining the design length and maximum design working load of the positioning tube, the following steps are also included:

[0062] Using the Monte Carlo sampling method, multiple existing data sets of design parameters of femoral fiber composite positioning tubes and corresponding multiple positioning tube lengths were obtained. The design parameters of femoral fiber composite positioning tubes included: femoral shell radius, number of carbon fiber layers of femoral shell, proportion of cancellous bone pore unit area and bone pore reduction coefficient.

[0063] The finite element model of the femoral fiber composite positioning tube was established through UG. According to the existing data sets of multiple groups of design parameters of the femoral fiber composite positioning tube and the corresponding multiple positioning tube lengths, Python was used to secondary develop ABAQUS simulation to construct a database of design parameters and deformation of the femoral fiber composite positioning tube.

[0064] The design parameters and deformation database of the femoral fiber composite positioning tube were preprocessed and the training set and test set were constructed. A BP neural network model for deformation calculation was constructed, and the training set and test set were used to train and test the BP neural network model to obtain the optimal BP neural network model.

[0065] The above BP neural network model, such as Fig.12 As shown, it includes: an input layer neural network, a hidden layer neural network and an output layer neural network, wherein: the input layer neural network includes: a femoral shell radius R input neural unit, a femoral shell carbon fiber layer number A input neural unit, a cancellous bone pore unit area proportion X input neural unit and a bone pore reduction coefficient θ input neural unit, the hidden layer neural network includes: 10 hidden neural units and a hidden layer bias bj1, the 10 hidden neural units are represented by Zj1, Zj2, Zj3, ..., Zj10 respectively, and the output layer neural network includes: a deformation output neural unit Y and an output layer bias bj2.

[0066] The above-mentioned use of the training set and the test set to train and test the BP neural network model to obtain the best BP neural network model includes:

[0067] The design parameters and deformation of the imitation femoral fiber composite positioning tube in the training set are weighted and summed with the connection weights of each implicit neural unit, and the value of each implicit neural unit is obtained through the activation function of the input layer, and the value of each implicit neural unit is weighted and summed with the connection weights of the corresponding output neural unit, and the first output deformation is obtained through the activation function of the output layer; wherein: the activation function of the input layer preferably adopts the logsig function, and the activation function of the output layer preferably adopts the sigmoid function with the steep slope factor λ. During back propagation, there is a flat area on the error surface, and the neuron output enters the saturation area of ​​the activation function. The steep slope factor λ is introduced to make it exit the saturation area of ​​the activation function. The initial value of the connection weight of the implicit neural unit contained in the Bone-BP neural network and the initial value of the connection weight of the output neural unit are generated by random numbers, and the initial value range is (0, 1).

[0068] The first output deformation is subtracted from the deformation in the training set to obtain a first error value, and the first error value is back-propagated through the BP neural network model to update the connection weights of each implicit neural unit and the connection weights of the output neural unit. Back-propagation uses the LM learning algorithm, which is a combination of the gradient descent method and the Gauss-Newton method. It uses approximate second-order derivative information, can effectively solve the problem of redundant parameters, and greatly reduces the chance of algebraic functions falling into local minima. The specific steps are as follows:

[0069] Multiplying the value obtained by the first error value LM learning algorithm by the learning rate η to obtain the adjustment value of the connection weight of each hidden neural unit and the adjustment amount of the connection weight of the output neural unit respectively;

[0070] The adjustment value of the connection weight of each hidden neural unit and the adjustment amount of the connection weight of the output neural unit are added to the connection weight of the current hidden neural unit and the connection weight of the output neural unit to obtain the updated connection weight of the hidden neural unit and the connection weight of the output neural unit.

[0071] The learning rate η adopts an adaptive method, and the initial value of the learning rate η is 1. If the current iteration error is greater than the learning rate η of the previous iteration error, the learning rate η is reduced, and the reduction range is (0, 1); if the current iteration error is less than the previous error or the current learning rate η is less than the set minimum value, the learning rate η is increased, and the increase value is greater than 1. By optimizing the learning rate algorithm, the iteration speed can be increased and the BP neural network training can be optimized. For example, the learning rate is initially 1, and after decaying once, the learning rate becomes 0.5, and the gain is taken as 5 once, and the learning rate becomes 2.5.

[0072] The updated connection weights of each hidden neural unit and the connection weights of the output neural unit are forward propagated again to obtain a second output deformation, and the second output deformation is subtracted from the deformation in the training set to obtain a second error value, and it is determined whether the second error value is greater than the target error value:

[0073] If yes, the second error value is back-propagated through the BP neural network model again to update the connection weights of each hidden neural unit and the connection weights of the output neural unit through loop iteration until it is less than or equal to the target error value, and then the next step is executed;

[0074] If no, proceed to the next step;

[0075] The connection weights of the current hidden layer neural units and the connection weights of the output neural units are saved, the training of the neural network is completed to obtain the best BP neural network model, and the performance of the best BP neural network model is tested through a test set.

[0076] Based on the above optimal BP neural network model and the database of design parameters and deformation of the femoral fiber composite positioning tube, the following introduces the value range of the design parameters of the femoral fiber composite positioning tube.

[0077] According to the obtained design length and maximum design working load of the positioning tube, the positioning tube is only subjected to unidirectional tensile load when working, and the strength design must satisfy σmax≤[σ]. The stress calculation formula for the positioning tube is as follows:

[0078] σ=F / S (1)

[0079] S=πR 2 (2)

[0080] σ max =σ / n (3)

[0081] Where: σ is the tensile strength, F is the working load, S is the area, R is the radius of the femoral shell, n is the safety factor, preferably 10, σ max For maximum strength.

[0082] According to the tensile strength of the imitation femoral fiber composite positioner, the working stress should not be greater than 65% of its tensile strength. The tensile strength of the imitation femoral fiber composite positioner σ w Using 410Mpa, based on the above formulas (1)-(3), the value range of R is R ≥ R min =6.0; the value range of R is selected as [6,8], and the value range of A is selected as [6,8] according to the positioner structure parameter-deformation database, the value range of X is selected as [30%, 50%], and the value range of θ is [1,2].

[0083] Step 102, normalizing the value range of the design parameters of the femoral bone imitating fiber composite material positioning tube to obtain the value range of the design parameters of the femoral bone imitating fiber composite material positioning tube after preprocessing.

[0084] Step 103, arranging and combining the value ranges of the pre-processed femoral fiber composite material positioning tube design parameters to obtain multiple sets of femoral fiber composite material positioning tube design parameter sets, and bringing the multiple sets of femoral fiber composite material positioning tube design parameter sets into the best BP neural network model obtained by training;

[0085] Step 104, using the optimal BP neural network model to obtain an optimal femoral fiber composite material positioning tube design parameter group, and modeling is performed according to the optimal femoral fiber composite material positioning tube design parameter group and the positioning tube length to obtain a positioning tube model.

[0086] As mentioned above, the optimal BP neural network model is used to obtain the optimal femoral fiber composite material positioning tube design parameter group, and the specific steps are as follows:

[0087] Using the best BP neural network model to obtain multiple deformation values, the multiple deformation values ​​are compared to obtain the minimum deformation data;

[0088] According to the minimum deformation data, multiple groups of femoral fiber composite material positioning tube design parameter sets are traversed to obtain the corresponding femoral fiber composite material positioning tube design parameter group, and the corresponding femoral fiber composite material positioning tube design parameter group is the optimal femoral fiber composite material positioning tube design parameter group.

[0089] Step 105, design a positioning connection point model and a positioning wire clamp model respectively according to the positioning tube model, and assemble the positioning tube model, the positioning connection point model and the positioning wire clamp model to obtain a locator model. Although the embodiments of the present invention have been disclosed as above, they are not limited to the applications listed in the specification and the implementation methods. It can be fully applied to various fields suitable for the present invention. For those familiar with the art, additional modifications can be easily implemented. Therefore, without departing from the general concept defined by the claims and the scope of equivalents, the present invention is not limited to the specific details and the illustrations shown and described herein.

Claims

1. A femoral fiber composite material positioner, characterized in that: The invention comprises a positioning tube (1), wherein the positioning tube (1) is connected to a positioning connection point (2) and a positioning wire clamp (3) at two ends thereof, respectively; the positioning tube (1) comprises a femoral shell, wherein a femoral imitation support structure and a filling support structure are arranged in the cavity of the femoral shell, and the bone porosity of the femoral imitation support structure gradually decreases in the direction from the positioning wire clamp (3) to the positioning connection point (2).

2. The femoral fiber composite material positioner according to claim 1, characterized in that: The simulated femoral support structure includes a compact bone pore unit area and a cancellous bone pore unit area. The compact bone pore unit area is adjacent to the femoral shell. The pore diameter of the compact bone pore unit area is smaller than the pore diameter of the cancellous bone pore unit area. The pores of the compact bone pore unit area and the pores of the cancellous bone pore unit area are both closed holes.

3. A femoral fiber composite material positioner according to claim 1 or 2, characterized in that: The femoral shell is formed by heating, pressurizing and curing a fiber resin layer, and the filling support structure is formed by secondary processing and curing of carbon fiber bundles and resin.

4. A design method for a femoral fiber composite material positioner, applied to a femoral fiber composite material positioner as claimed in any one of claims 1 to 3, characterized in that: include: Obtaining the design length and the maximum design working load of the positioning tube, and determining the value range of the design parameters of the femoral fiber composite material positioning tube according to the length and the maximum working load of the positioning tube; Normalizing the value range of the design parameter of the femoral imitation fiber composite material positioning tube to obtain the value range of the design parameter of the femoral imitation fiber composite material positioning tube after preprocessing; Arrange and combine the value ranges of the pre-processed femoral fiber composite material positioning tube design parameters to obtain multiple sets of femoral fiber composite material positioning tube design parameter sets, and bring the multiple sets of femoral fiber composite material positioning tube design parameter sets into the best BP neural network model obtained by training; The optimal BP neural network model is used to obtain an optimal femoral imitation fiber composite material positioning tube design parameter group, and a positioning tube model is obtained by modeling according to the optimal femoral imitation fiber composite material positioning tube design parameter group and the positioning tube length; A positioning connection point model and a positioning wire clamp model are designed respectively according to the positioning tube model, and the positioning tube model, the positioning connection point model and the positioning wire clamp model are assembled to obtain a locator model.

5. The design method of a femoral imitation fiber composite material positioning tube according to claim 4, characterized in that: Before obtaining the design length and maximum design working load of the positioning tube, it also includes: Acquire multiple existing data sets of design parameters of femoral fiber composite positioning tubes and corresponding multiple positioning tube lengths; A finite element model of a femoral fiber composite positioning tube is established, and a database of femoral fiber composite positioning tube design parameters and deformation values ​​is constructed by using Python secondary development of ABAQUS simulation according to multiple existing data sets of femoral fiber composite positioning tube design parameters and corresponding multiple positioning tube lengths; Preprocessing the design parameters and deformation database of the femoral fiber composite material positioning tube and constructing a training set and a test set; A BP neural network model for deformation calculation is constructed, and the BP neural network model is trained and tested using the training set and the test set to obtain an optimal BP neural network model.

6. The design method of a femoral imitation fiber composite material positioning tube according to claim 5, characterized in that: The design parameters of the femoral fiber composite material positioning tube include: the radius of the femoral shell, the number of carbon fiber layers of the femoral shell, the proportion of the cancellous bone pore unit area and the bone pore reduction coefficient. The BP neural network model includes: an input layer neural network, a hidden layer neural network and an output layer neural network, wherein: The input layer neural network includes: a femoral shell radius input neural unit, a femoral shell carbon fiber layer number input neural unit, a cancellous bone pore unit area ratio input neural unit and a bone pore reduction coefficient input neural unit; the hidden layer neural network includes: 10 hidden neural units and a hidden layer bias; the output layer neural network includes: a deformation output neural unit and an output layer bias.

7. The design method of a femoral imitation fiber composite material positioning tube according to claim 6, characterized in that: The method of using the training set and the test set to train and test the BP neural network model to obtain the best BP neural network model includes: The design parameters and deformation of the femoral fiber composite material positioning tube in the training set are weighted and summed with the connection weights of each implicit neural unit, and the value of each implicit neural unit is obtained through the activation function of the input layer, and the value of each implicit neural unit is weighted and summed with the connection weights of the corresponding output neural unit, and the first output deformation is obtained through the activation function of the output layer; Subtract the first output deformation from the deformation in the training set to obtain a first error value, and back-propagate the first error value through the BP neural network model to update the connection weights of each hidden neural unit and the connection weights of the output neural unit; The updated connection weights of each hidden neural unit and the connection weights of the output neural unit are forward propagated again to obtain a second output deformation, and the second output deformation is subtracted from the deformation in the training set to obtain a second error value, and it is determined whether the second error value is greater than the target error value: If yes, the second error value is back-propagated through the BP neural network model again to update the connection weights of each hidden neural unit and the connection weights of the output neural unit through loop iteration until it is less than or equal to the target error value, and then the next step is executed; If no, proceed to the next step; The connection weights of the current hidden layer neural units and the connection weights of the output neural units are saved, the training of the neural network is completed to obtain the best BP neural network model, and the performance of the best BP neural network model is tested through a test set.

8. The design method of a femoral imitation fiber composite material positioning tube according to claim 7, characterized in that: The activation function of the input layer adopts the logsig function, and the activation function of the output layer adopts the sigmoid function.

9. The design method of a femoral imitation fiber composite material positioning tube according to claim 8, characterized in that: The method of back-propagating the first error value through the BP neural network model to update the connection weights of each implicit neural unit and the connection weights of the output neural unit includes: Multiplying the value obtained by the LM learning algorithm of the first error value by the learning rate to obtain the adjustment value of the connection weight of each hidden neural unit and the adjustment amount of the connection weight of the output neural unit; The adjustment value of the connection weight of each hidden neural unit and the adjustment amount of the connection weight of the output neural unit are added to the connection weight of the current hidden neural unit and the connection weight of the output neural unit to obtain the updated connection weight of the hidden neural unit and the connection weight of the output neural unit.

10. The design method of a femoral imitation fiber composite material positioning tube according to claim 4, characterized in that: The method of using the optimal BP neural network model to obtain the optimal femoral fiber composite material positioning tube design parameter group includes: Using the optimal BP neural network model to obtain multiple deformation values, and comparing the multiple deformation values ​​to obtain minimum deformation data; According to the minimum deformation data, multiple groups of femoral fiber composite material positioning tube design parameter sets are traversed to obtain the corresponding femoral fiber composite material positioning tube design parameter group, and the corresponding femoral fiber composite material positioning tube design parameter group is the optimal femoral fiber composite material positioning tube design parameter group.

Images