A method and system for intelligently detecting the meshing rate of an injection molded gear of an automobile

Abstract

The application provides a kind of intelligent detection method and system of automobile injection gear engagement rate, it is related to material testing and analysis technical field, method includes: based on three-dimensional laser scanning obtains meshing surface geometric characteristic parameter;Through piezoelectric sensor array and finite element model calculation dynamic contact stress distribution index;Utilize high-speed camera system and image processing algorithm determine profile deviation fluctuation coefficient;Build machine learning comprehensive evaluation model and output three-dimensional index;According to the evaluation result, generate adaptive grinding scheme and closed-loop control processing.The application solves the problem of traditional method relying on artificial and single detection dimension through multi-source data fusion and intelligent optimization, realizes dynamic contact characteristic accurate analysis and real-time correction of processing parameter, significantly improves detection precision and production efficiency.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of material testing and analysis technology, in particular to a kind of intelligent detection method and system of automobile injection molding gear. BACKGROUND

[0002] In the contact performance detection of automobile injection molding gear, the traditional method mainly relies on red powder contact method and artificial visual evaluation. When operating, red powder is applied on the surface of the gear, and the contact quality is judged by the distribution of contact spots after meshing, but this method can only reflect the static contact state, and cannot capture the stress change and tooth profile deviation fluctuation in the dynamic meshing process. Artificial interpretation is highly subjective, with low quantitative accuracy, and cannot identify microscopic topographic defects, resulting in insufficient reliability of the detection results, making it difficult to meet the manufacturing needs of high-precision gears.

[0003] Existing technologies attempt to introduce single-point stress sensors or two-dimensional image analysis methods to improve objectivity, but still have significant limitations. Single-point sensors can only obtain local stress data, and cannot fully represent the stress distribution characteristics of the contact area, resulting in a high rate of missed detection of abnormal stress concentration areas. Although two-dimensional image analysis can identify contact trajectory deviation, it lacks depth information of three-dimensional morphology and cannot quantify key parameters such as tooth surface waviness, making it difficult to accurately assess contact stability under dynamic meshing.

[0004] Current detection systems generally use isolated data acquisition and analysis modules, and geometric parameters, mechanical properties and dynamic behavior data lack effective coordination. The detection results are disconnected from the processing and correction process, and rely on manual experience to repeatedly test and adjust grinding parameters, which not only reduces efficiency, but also easily leads to a decrease in gear strength due to excessive shaping. In addition, existing methods do not construct a real-time feedback closed-loop control mechanism, making it difficult to achieve intelligent optimization of detection-processing integration. SUMMARY

[0005] To solve the technical problems of single detection method, reliance on manual experience, inability to dynamically analyze gear contact characteristics in real time, and lack of intelligent closed-loop control in existing technologies, the present application provides an intelligent detection method and system for automobile injection molding gear.

[0006] The technical solutions provided by the present application are as follows:

[0007] First aspect:

[0008] The intelligent detection method for automobile injection molding gear provided by the present application comprises:

[0009] S1, collecting three-dimensional topographic data of the gear meshing surface based on a three-dimensional laser scanner (3D Laser Scanner), to obtain a set of geometric characteristic parameters of the tooth surface contact area, the set of geometric characteristic parameters at least including contact spot distribution density, contact trajectory offset, and tooth surface waviness;

[0010] S2, constructing a dynamic contact stress distribution index (DCSDI), collecting a contact stress time domain signal in real time through a piezoelectric stress sensor array installed on a gear test bench, and calculating the dynamic contact stress distribution index in combination with a finite element contact analysis model;

[0011] S3, establishing a profile deviation fluctuation coefficient (PDFC), synchronously capturing a contact trajectory image sequence of a gear pair meshing process by using a high-speed camera system, and obtaining time sequence variation characteristics of profile deviation by using an image feature extraction algorithm;

[0012] S4, inputting the dynamic contact stress distribution index and the profile deviation fluctuation coefficient into a meshing rate comprehensive evaluation model, the model performing multi-dimensional matching analysis on the two characteristic parameters and a standard meshing rate database through a machine learning algorithm, and outputting three-dimensional evaluation indexes including a contact area qualified rate, a stress distribution uniformity, and a dynamic matching accuracy;

[0013] S5, generating a contact optimization scheme according to the three-dimensional evaluation indexes, performing adaptive grinding processing on the gear meshing surface through a numerical control modification device, and feeding back and correcting processing parameters in real time until a preset meshing rate threshold is reached.

[0014] Further, the calculation method of the dynamic contact stress distribution index comprises:

[0015]

[0016] wherein σ max is a maximum stress value of the contact area, in MPa, σ avg is an average stress value of the contact area, in MPa, N c is a stress concentration coefficient, determined according to a gear contact strength calculation method in the ISO 6336 standard, and ΔA is an abnormal stress area, in mm 2 , A0 is a theoretical contact area, in mm 2 The calculation process specifically comprises: performing spatial interpolation processing on stress data collected by the piezoelectric sensor array, generating a contact stress cloud map, identifying an abnormal stress area by using a region segmentation algorithm, and performing area integral calculation in combination with a grid division result of the finite element model.

[0017] Further, the method for determining the profile deviation fluctuation coefficient comprises:

[0018]

[0019] Wherein, T is the complete meshing period, unit s, ΔF p (t) is the dynamic change of the pitch deviation, unit μm, F p0 is the pitch tolerance reference value, unit μm, Δf Hα (t) is the dynamic change of the profile tilt deviation, unit μm, f Hα0 is the profile tilt tolerance reference value, unit μm, the calculation process comprises: sub-pixel edge detection on the contact trajectory image obtained by the high-speed camera system, using a space-time filtering algorithm to eliminate the motion blur effect, and then reversing the profile deviation parameters through the gear meshing kinematics model.

[0020] Further, the method for constructing the comprehensive evaluation model in S4 comprises:

[0021] An improved analytic hierarchy process (IAHP) is used to determine the weight distribution of each evaluation index, wherein a contact trajectory optimization algorithm is used to calculate a weight correction factor:

[0022]

[0023] Wherein, w i is the initial weight, α is the system stability coefficient, ranging from 0.1 to 0.3, β is the parameter sensitivity adjustment factor, ranging from 0.5 to 1.2, C i is the confidence of the characteristic parameter, which is calculated and determined according to the measurement uncertainty corresponding to the gear accuracy grade in the ISO 1328-1:2013 standard.

[0024] Further, the contact trajectory optimization algorithm uses a hybrid optimization strategy of genetic algorithm (GA) and particle swarm optimization (PSO):

[0025] Wherein, the fitness function is defined as:

[0026]

[0027] Wherein, k1, k2, k3 are weighting coefficients, satisfying k1+k2+k3=1, S contact is the ratio of the actual contact area to the theoretical contact area, the crossover probability P c and the mutation probability P mAccording to the population diversity index dynamic adjustment.

[0028] Further, the finite element contact analysis model in S2 adopts a Johnson-Cook dynamic constitutive model to describe material properties: the expression is as follows:

[0029]

[0030] wherein A is a material yield stress, the unit is MPa, B is a strain hardening coefficient, n is a strain hardening index, C is a strain rate sensitivity coefficient, and ε is an equivalent plastic strain, is a dimensionless strain rate, T is a relative temperature, and the model parameters are obtained by automatic matching of a material test database.

[0031] Further, the image feature extraction algorithm in S3 adopts an improved Canny edge detection algorithm, and the contact trajectory is identified in combination with gear meshing phase information, wherein a non-maximum value suppression threshold is dynamically adjusted according to an image signal-to-noise ratio:

[0032]

[0033] T l = 0.4 x T h

[0034] wherein σ n is an image noise standard deviation, I max , I min are maximum and minimum gray scale values of the image respectively, and k is an empirical coefficient, the range is 0.8-1.2, and the algorithm is realized on an FPGA chip for real-time processing.

[0035] The second aspect is:

[0036] The application provides an intelligent detection system for a research and mixing rate of an automobile injection molded gear, which comprises:

[0037] A three-dimensional scanning module is configured with a laser interferometer and a confocal displacement sensor, and is used for acquiring micro-topography data of a gear meshing surface.

[0038] A stress analysis module comprises an annularly distributed piezoelectric stress sensor array and a high-speed data acquisition card, and is used for monitoring a contact stress distribution in real time.

[0039] An image processing module is integrated with a double-CCD high-speed camera and an LED pulse light source, and is used for capturing dynamic images of meshing contact trajectories.

[0040] A calculation center is equipped with a GPU parallel computing unit, and is used for running a finite element contact analysis model and a machine learning evaluation model.

[0041] A feedback control module comprises a numerical control grinding machine and an adaptive PID controller, which automatically adjusts the processing parameters according to the evaluation results.

[0042] Further, the piezoelectric stress sensor array of the stress analysis module is arranged in a concentric circle, the spacing between adjacent sensors is less than 1.5 mm, and the calculation center is connected through an optical fiber transmission protocol; the double-CCD high-speed camera of the image processing module is arranged at a 90° orthogonal angle, and the frame rate is not less than 2000 fps.

[0043] Further, the numerical control grinding machine of the feedback control module comprises a five-axis linkage mechanical arm and a diamond grinding head, the grinding pressure control precision is ±0.1N, and the position repeatability precision is ±2μm; the adaptive PID controller and the calculation center interact through a real-time Ethernet protocol.

[0044] The technical scheme provided by the application has at least the following beneficial effects:

[0045] (1) In the application, three-dimensional topography scanning, dynamic stress analysis and tooth profile deviation dynamic monitoring technology are fused to construct a multi-dimensional data collaborative detection system, which significantly improves the comprehensiveness and accuracy of the detection. High-precision sensor array and high-speed image processing technology are used to realize real-time synchronous acquisition of contact stress distribution and tooth profile deviation, overcoming the limitations of traditional single-point detection. Combined with a machine learning evaluation model, abnormal areas under complex contact modes can be automatically identified, avoiding subjective errors of manual interpretation, greatly shortening the detection period and ensuring the quality consistency in batch production.

[0046] (2) In the application, based on the feedback control mechanism of the dynamic evaluation index, the detection results are intelligently associated with the processing parameters to automatically generate a targeted grinding scheme. Through multi-axis linkage precision machining equipment and adaptive control algorithm, the grinding pressure, path and speed are dynamically adjusted to effectively eliminate local stress concentration and tooth profile deviation. This closed-loop control strategy can reduce material waste caused by traditional trial-and-error processing, improve the contact uniformity and carrying capacity of the gear pair, prolong the service life, and reduce the dependence on the experience of operators.

[0047] (3) In the application, the topography acquisition, stress analysis, image processing and numerical control machining modules are deeply integrated to construct a full-process intelligent detection-machining system. Through a unified data interface and real-time communication protocol, the modules are efficiently coordinated to avoid data discontinuity caused by multiple device switching. The embedded expert knowledge base and optimization algorithm support rapid adaptation of multiple types of gears, significantly improving the flexible production capacity of the production line and providing a complete solution for the digital upgrade of gear manufacturing. BRIEF DESCRIPTION OF DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed in the embodiment description. Obviously, the drawings in the following description only show some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without any creative effort.

[0049] Figure 1 A flowchart of an intelligent detection method for a grinding rate of an automobile injection molded gear provided by the embodiment of the present application is shown in the figure.

[0050] Figure 2 A structural schematic diagram of an intelligent detection system for a grinding rate of an automobile injection molded gear provided by the embodiment of the present application is shown in the figure.

[0051] Figure 3 A data flow and processing logic schematic diagram of an intelligent detection system for a grinding rate of an automobile injection molded gear provided by the embodiment of the present application is shown in the figure.

[0052] In the figure: 301, three-dimensional scanning module; 302, stress analysis module; 303, image processing module; 304, calculation center; 305, feedback control module. DETAILED DESCRIPTION

[0053] The technical solutions in the present application will be described below with reference to the drawings.

[0054] In the embodiments of the present application, the words such as "example", "for example" and the like are used to represent as an example, illustration or description. Any embodiment or design scheme described as "example" in the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, the word "example" is intended to present the concept in a specific manner. In addition, in the embodiments of the present application, the meaning expressed by "and / or" can be both, or can be one of the two.

[0055] In the embodiments of the present application, "image" and "picture" can be used interchangeably at times. It should be pointed out that when the distinction is not emphasized, the meanings expressed are consistent. The words "of", "corresponding" and "relevant" can be used interchangeably at times. It should be pointed out that when the distinction is not emphasized, the meanings expressed are consistent.

[0056] In the embodiments of the present application, sometimes the subscript such as W1 can be mistakenly used in the form of non-subscript such as W1. When the distinction is not emphasized, the meanings expressed are consistent.

[0057] In order to make the technical problems, technical solutions and advantages of the present application more clear, the following will be described in detail with reference to the drawings and specific embodiments.

[0058] With reference to the accompanying drawings Figure 1 , a flowchart of a method for intelligently detecting a meshing rate of an automobile injection molded gear is shown.

[0059] The embodiment of the application provides a kind of automobile injection molded gear's meshing rate intelligent detection method, this method can be realized by a kind of automobile injection molded gear's meshing rate intelligent detection equipment, the automobile injection molded gear's meshing rate intelligent detection equipment can be terminal or server, the processing flow of a kind of automobile injection molded gear's meshing rate intelligent detection method can include the following steps:

[0060] S1, based on three-dimensional laser scanner, the three-dimensional topographic data of gear meshing surface is collected, the geometric characteristic parameter set of tooth surface contact area is obtained, and the geometric characteristic parameter set at least includes contact spot distribution density, contact trajectory offset and tooth surface waviness.

[0061] In a possible implementation, Keyence LJ-V7300 three-dimensional laser scanner is used, with a lateral resolution of 5 μm and a longitudinal repeat accuracy of 0.1 μm. When scanning, the gear is installed on an air floating turntable (radial runout ≤2 μm) and rotates at a constant speed of 10 r / min. After denoising the collected meshing surface point cloud data by Gaussian filtering (σ = 0.1 mm), the following geometric characteristic parameters are extracted:

[0062] Contact spot distribution density: the contact spots are identified by Otsu adaptive threshold segmentation method, and the density formula is:

[0063]

[0064] Wherein, N spot is the number of spots, A contact is the contact area, and the qualified range is 150-400 per cm 2 .

[0065] Contact trajectory offset: based on the theoretical involute equation of gear parameters, the actual trajectory is fitted by cubic B-spline, and the root mean square deviation (RMS) is calculated, with a maximum allowable deviation of ≤15 μm.

[0066] Tooth surface waviness: wavelet analysis is used to extract surface components with a wavelength of 0.1-1 mm, and the amplitude threshold is set to ±2 μm. The area exceeding the threshold is marked as the grinding target.

[0067] S2, construct dynamic contact stress distribution index DCSDI, real-time collect contact stress time domain signal through piezoelectric stress sensor array installed on gear test bench, and obtain dynamic contact stress distribution index by combining finite element contact analysis model.

[0068] In a possible implementation, 16 Kistler 9313B piezoelectric stress sensors are installed on the gear test bench in a helical distribution (pitch angle 15°), with a sampling frequency of 10 kHz, and the signals are conditioned by an NI PXIe-4330 module. A gear contact model is built based on ANSYS Workbench, with a grid size of 0.2 mm, and a Johnson-Cook dynamic constitutive equation is used for the material model:

[0069]

[0070] The parameters are set as follows: A = 80 MPa, B = 120 MPa, n = 0.35, C = 0.015, m = 1.2, reference strain rate 1.0 s -1 , and temperature parameter T* = (T-25) / 235.

[0071] According to the formula

[0072]

[0073] where σ max and σ avg are obtained by stress cloud interpolation, N c is calculated according to ISO 6336-2019, and ΔA is the area of the abnormal stress region (integrated by the finite element grid). Example: when σ max = 85 MPa, σ avg = 32 MPa, N c = 1.8, ΔA = 3.2 mm 2 , A0 = 25.6 mm 2 , DCSDI = 2.89, and the threshold value is 3.0, processing is triggered.

[0074] S3, establish the profile deviation fluctuation coefficient PDFC, use a high-speed camera system to synchronously capture the contact trajectory image sequence of the gear pair meshing process, and obtain the time sequence variation characteristics of the profile deviation by image feature extraction algorithm.

[0075] In a possible implementation, a Photron FASTCAM Nova S12 high-speed camera (resolution 1280×1024, frame rate 5000 fps) is used, equipped with a 630 nm narrowband filter and a pulse LED light source (pulse width 50 μs), and a synchronous encoder is used to obtain the gear speed.

[0076] According to the speed ω (rad / s), the blur length L = w × r × t exp is calculated, and the Richardson-Lucy deconvolution is used to restore the image. Based on the Zernike moment algorithm, the edge is located with an accuracy of 0.1 pixels.

[0077] According to the formula

[0078]

[0079] Where, T = 0.2 s (corresponding to 2000 r / min), ΔF p (t) fluctuation ± 12 μm (f p0 = 20 μm), Δf Hα (t) fluctuation ± 8 μm (f Hα0 = 15 μm), calculated result PDFC = 0.68, qualified threshold ≤ 0.7.

[0080] S4, input the dynamic contact stress distribution index and the tooth profile deviation fluctuation coefficient into the meshing rate comprehensive evaluation model, the model performs multi-dimensional matching analysis on the two characteristic parameters and the standard meshing rate database through a machine learning algorithm, and outputs three-dimensional evaluation indexes including a contact area qualified rate, a stress distribution uniformity, and a dynamic matching accuracy.

[0081] In a possible implementation, an improved analytic hierarchy process (IAHP) is adopted to construct a judgment matrix (contact area qualified rate: stress distribution uniformity: dynamic matching accuracy = 1:1.5:2), to calculate an initial weight w = [0.45, 0.35, 0.20], and to correct the initial weight through a correction factor formula:

[0082]

[0083] Adjustment parameters α = 0.2, β = 0.8, C_i = 0.92 (measured uncertainty according to ISO 1328-1), and the corrected weight is [0.53, 0.40, 0.22]. Genetic algorithm (population size 200, crossover probability Pc = 0.8-0.2 linearly decreasing) and particle swarm optimization (inertia weight ω = 0.9-0.4) are combined, and a fitness function is:

[0084]

[0085] Where, S contact is a ratio of an actual contact area to a theoretical value, and an optimization target is Fitness ≥ 0.85.

[0086] S5, generate a contact optimization scheme according to the three-dimensional evaluation indexes, perform adaptive grinding processing on a gear meshing surface through a numerical control modification device, and feed back and correct processing parameters in real time until a preset meshing rate threshold is reached.

[0087] In a possible implementation, the processing parameters are mapped as follows:

[0088] Contact area qualification rate Grinding pressure (N) Feed speed (mm / s) Path overlap rate <70％ 8.0±0.5 15 40％ 70％-85％ 6.5±0.3 20 30％ >85％ 5.0±0.2 25 20％

[0089] Adopting TX2-90L five-axis robotic arm (repeatability ±2μm), grinding pressure control accuracy ±0.1N, PID parameters adjusted according to rules:

[0090] K p =2.5×(1-S contact )

[0091] K i =0.8 / K p

[0092] K d =0.05×σ max

[0093] After machining every 3 tooth surfaces, a re-detection is triggered until DCSDI < 3.0 and PDFC < 0.7 for 3 consecutive times.

[0094] This invention also provides an intelligent detection system for the lapping rate of automotive injection molded gears, applied to the aforementioned intelligent detection method for the lapping rate of automotive injection molded gears, comprising:

[0095] like Figure 2 As shown, this system consists of a 3D scanning module 301, a stress analysis module 302, an image processing module 303, a computing center 304, and a feedback control module 305. The 3D scanning module 301 includes a laser interferometer and a confocal displacement sensor, transmitting 3D topographic data to the computing center 304 via a PCIe interface. The ring piezoelectric sensor array of the stress analysis module 302 synchronizes via the IEEE 1588 protocol, sending dynamic stress data to the computing center 304. The dual CCD cameras and FPGA chip of the image processing module 303 output tooth profile deviation data to the computing center 304 in real time. The computing center 304 integrates a GPU parallel computing unit, a machine learning evaluation model, and an expert knowledge base. After receiving all detection data, it generates processing instructions and sends them to the five-axis robotic arm and grinding head of the feedback control module 305 via the EtherCAT protocol. The feedback control module 305 transmits the processing status back to the computing center 304 in real time, forming a detection-processing closed loop.

[0096] The system includes a 3D scanning module equipped with a laser interferometer and a confocal displacement sensor to acquire microscopic morphological data of the gear meshing surface; a stress analysis module containing a ring-shaped piezoelectric stress sensor array and a high-speed data acquisition card to monitor the contact stress distribution in real time; an image processing module integrating a dual CCD high-speed camera and an LED pulse light source to capture dynamic images of the meshing contact trajectory; a computing center equipped with a GPU parallel computing unit to run finite element contact analysis models and machine learning evaluation models; and a feedback control module containing a CNC grinding machine and an adaptive PID controller to automatically adjust processing parameters based on evaluation results.

[0097] In one possible implementation, the piezoelectric stress sensor array of the stress analysis module is arranged in concentric circles, with the spacing between adjacent sensors being less than 1.5 mm, and is connected to the computing center via an optical fiber transmission protocol; the dual CCD high-speed cameras of the image processing module are arranged at a 90° orthogonal angle, with a frame rate of not less than 2000 fps.

[0098] In one possible implementation, the CNC grinding machine of the feedback control module includes a five-axis linkage robotic arm and a diamond grinding head, with a grinding pressure control accuracy of ±0.1N and a position repeatability accuracy of ±2μm; the adaptive PID controller interacts with the computing center via a real-time Ethernet protocol.

[0099] like Figure 3 As shown, the data flow begins with the contact spot distribution density, trajectory offset, and tooth surface waviness output by the 3D scanning module 301, which are input to the geometric feature fusion unit of the computing center 304. The stress cloud map and DCSDI index provided by the stress analysis module 302 are input to the mechanical performance analysis unit. The sub-pixel edge coordinates and PDFC coefficients of the image processing module 303 are input to the dynamic behavior evaluation unit. The computing center 304 fuses multi-source data through a comprehensive evaluation model, calls a hybrid algorithm library of genetic algorithm and particle swarm optimization to generate optimal processing parameters, and outputs grinding pressure, path planning, and speed commands to the feedback control module 305. After the feedback control module 305 executes the processing, it triggers the re-inspection process of the 3D scanning module 301, stress analysis module 302, and image processing module 303, forming a closed-loop verification. The data flow of each module is unidirectional and progressive, and finally returns to the initial detection end through processing effect verification.

[0100] In one possible implementation, the 3D scanning module uses a Keyence LJ-V7300 to transmit data to the computing center via a PCIe 3.0 x8 interface (6GB / s bandwidth). The stress analysis module uses Kistler 9313B sensors arranged in concentric circles (1.5mm spacing) and synchronized via the IEEE 1588 protocol (time jitter <1μs). The image processing module uses a Xilinx Kintex-7 FPGA to implement the Canny algorithm, with dynamic threshold calculation as follows:

[0101]

[0102] Parameters k = 1.0, σ n =2.3-3.5 (standard deviation of dark field noise), processing delay <2ms.

[0103] The computing center runs a PyTorch model for a NVIDIA A100 GPU, and the database contains Johnson-Cook parameters and ISO failure thresholds of materials such as PA66 and PEEK. The feedback control module controls a five-axis grinder with an EtherCAT protocol (cycle 1 ms), and the grinding head has a granularity of #2000 and a surface roughness Ra≤0.1 μm.

[0104] The technical scheme provided by the embodiments of the present application brings at least the following beneficial effects:

[0105] (1) In the present application, by fusing three-dimensional topography scanning, dynamic stress analysis and tooth profile deviation dynamic monitoring technology, a multi-dimensional data collaborative detection system is constructed, which significantly improves the comprehensiveness and accuracy of the detection. High-precision sensor array and high-speed image processing technology are used to realize real-time synchronous acquisition of contact stress distribution and tooth profile deviation, overcoming the limitations of traditional single-point detection. Combined with machine learning evaluation model, abnormal areas under complex contact mode can be automatically identified, avoiding subjective errors of manual interpretation, greatly shortening the detection period and ensuring the quality consistency in batch production.

[0106] (2) In the present application, based on the feedback control mechanism of dynamic evaluation index, the detection results are intelligently associated with the processing parameters to automatically generate a targeted grinding scheme. Through multi-axis linkage precision machining equipment and adaptive control algorithm, the grinding pressure, path and speed are dynamically adjusted to effectively eliminate local stress concentration and tooth profile deviation. This closed-loop control strategy can reduce material waste caused by traditional trial-and-error processing, improve the contact uniformity and carrying capacity of the gear pair, prolong the service life, and reduce the dependence on operator experience.

[0107] (3) In the present application, the topography acquisition, stress analysis, image processing and numerical control machining modules are deeply integrated to construct a full-process intelligent detection-machining system. Through unified data interface and real-time communication protocol, efficient collaboration of each module is realized, avoiding data discontinuity caused by multiple device switching. The embedded expert knowledge base and optimization algorithm support rapid adaptation of multiple types of gears, significantly improving the flexible production capacity of the production line and providing a complete solution for the digital upgrade of gear manufacturing.

[0108] The above is only a specific embodiment of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0109] The following points need to be explained:

[0110] (1) The drawings of the embodiments of the present application only relate to the structures involved in the embodiments of the present application, and other structures can be referred to the general design.

[0111] (2) In the drawings used to describe the embodiments of the present application, the thickness of a layer or region is exaggerated or reduced for clarity, i.e., the drawings are not drawn according to the actual scale. It can be understood that when an element such as a layer, film, region or substrate is referred to as being "on" or "under" another element, it can be "directly" on or under the other element or there can be an intermediate element.

[0112] (3) In the case of no conflict, the embodiments of the present application and the features in the embodiments can be combined with each other to obtain new embodiments.

[0113] The above is only a specific embodiment of the present application, but the protection scope of the present application is not limited thereto, and the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for intelligent detection of the meshing rate of injection-molded automotive gears, characterized in that, include: S1. Based on a 3D laser scanner, collect 3D topographic data of the gear meshing surface and obtain a set of geometric feature parameters of the tooth surface contact area. The set of geometric feature parameters includes at least the contact spot distribution density, contact trajectory offset and tooth surface waviness. S2. Construct the Dynamic Contact Stress Distribution Index (DCSDI). The dynamic contact stress distribution index is obtained by real-time acquisition of contact stress time-domain signals through a piezoelectric stress sensor array installed on the gear test bench and combined with the finite element contact analysis model. The calculation method for the dynamic contact stress distribution index includes: ； in, This represents the maximum stress value in the contact area, in MPa. The average stress value in the contact area is expressed in MPa. The stress concentration factor is determined according to the gear contact strength calculation method in ISO 6336 standard. This represents the area of ​​the abnormal stress region, in mm². The theoretical contact area is in mm². The calculation process specifically includes: spatial interpolation processing of the stress data collected by the piezoelectric sensor array to generate a contact stress cloud map; using a region segmentation algorithm to identify abnormal stress regions; and performing area integration calculation in combination with the mesh division results of the finite element model. S3. Establish the tooth profile deviation fluctuation coefficient PDFC, use a high-speed camera system to synchronously capture the contact trajectory image sequence of the gear pair meshing process, and obtain the temporal variation characteristics of the tooth profile deviation through image feature extraction algorithm; The method for determining the tooth profile deviation fluctuation coefficient includes: ； in, The complete meshing cycle is measured in seconds (s). This represents the dynamic change in pitch deviation, in units of... , This is the reference value for the pitch tolerance, in units of... , This represents the dynamic change in tooth profile inclination deviation, in units of... , This is the reference value for the tooth profile inclination tolerance, in units of The calculation process includes: performing sub-pixel edge detection on the contact trajectory image acquired by the high-speed camera system, eliminating the effect of motion blur by using a spatiotemporal filtering algorithm, and then inversely calculating the tooth profile deviation parameters through a gear meshing kinematic model; S4. Input the dynamic contact stress distribution index and the tooth profile deviation fluctuation coefficient into the comprehensive evaluation model of the lapping rate. This model uses a machine learning algorithm to perform multi-dimensional matching analysis between the two feature parameters and the standard lapping rate database, and outputs a three-dimensional evaluation index including the contact area qualification rate, stress distribution uniformity and dynamic matching accuracy. S5. Generate a contact optimization scheme based on the three-dimensional evaluation index, perform adaptive grinding on the gear meshing surface using CNC shaping equipment, and provide real-time feedback to correct the processing parameters until the preset grinding rate threshold is reached.

2. The intelligent detection method for the lapping rate of automotive injection molded gears according to claim 1, characterized in that, The construction method of the comprehensive evaluation model for the research and development rate described in S4 includes: The weight allocation of each evaluation index was determined using the improved analytic hierarchy process (IAHP), in which a contact trajectory optimization algorithm was introduced to calculate the weight correction factor. ； in, As the initial weights, This is the system stability coefficient, ranging from 0.1 to 0.

3. This is a parameter sensitivity adjustment factor, ranging from 0.5 to 1.

2. The confidence level of the characteristic parameter is calculated and determined according to the measurement uncertainty corresponding to the gear accuracy class in ISO 1328-1:2013 standard.

3. The intelligent detection method for the meshing rate of automotive injection molded gears according to claim 2, characterized in that, The contact trajectory optimization algorithm adopts a hybrid optimization strategy of genetic algorithm (GA) and particle swarm optimization (PSO): The fitness function is defined as follows: ； in, , , For the weighting coefficients, satisfying , The ratio of the actual contact area to the theoretical contact area, and the crossover probability of the genetic algorithm. and mutation probability Adjusted dynamically based on the population diversity index.

4. The intelligent detection method for the meshing rate of automotive injection molded gears according to claim 1, characterized in that, The finite element contact analysis model described in S2 uses the Johnson-Cook dynamic constitutive model to describe material properties: the expression is: ； in, The yield stress of the material is expressed in MPa. For strain hardening coefficient, The strain hardening index is... The strain rate sensitivity coefficient, For equivalent plastic strain, The strain rate is dimensionless. The relative temperature is used, and the model parameters are automatically obtained by matching from the material testing database.

5. The intelligent detection method for the lapping rate of automotive injection molded gears according to claim 1, characterized in that, The image feature extraction algorithm described in S3 employs an improved Canny edge detection algorithm, combined with gear meshing phase information for contact trajectory recognition. The non-maximum suppression threshold is dynamically adjusted based on the image signal-to-noise ratio. ； ； in, The standard deviation of image noise. , These are the maximum and minimum grayscale values ​​of the image, respectively. The coefficient is an empirical value, ranging from 0.8 to 1.

2. The algorithm is implemented in real time on an FPGA chip.

6. An intelligent detection system for the lapping rate of automotive injection molded gears, used to implement the intelligent detection method for the lapping rate of automotive injection molded gears as described in claims 1 to 5, characterized in that, include: The three-dimensional scanning module (301) is equipped with a laser interferometer and a confocal displacement sensor to acquire microscopic morphological data of the gear meshing surface; The stress analysis module (302) includes a ring-shaped piezoelectric stress sensor array and a high-speed data acquisition card to monitor the contact stress distribution in real time; The image processing module (303) integrates a dual CCD high-speed camera and an LED pulse light source to capture dynamic images of the meshing contact trajectory; The computing center (304) is equipped with GPU parallel computing units for running finite element contact analysis models and machine learning evaluation models; The feedback control module (305) includes a CNC grinding machine and an adaptive PID controller, which automatically adjusts the processing parameters based on the evaluation results.

7. The intelligent detection system for the meshing rate of automotive injection molded gears according to claim 6, characterized in that, include: The piezoelectric stress sensor array of the stress analysis module (302) is arranged in concentric circles with a spacing of less than 1.5 mm between adjacent sensors, and is connected to the computing center (304) via an optical fiber transmission protocol; the dual CCD high-speed cameras of the image processing module (303) are arranged at a 90° orthogonal angle with a frame rate of not less than 2000fps.

8. The intelligent detection system for the meshing rate of automotive injection molded gears according to claim 6, characterized in that, include: The feedback control module (305) of the CNC grinding machine includes a five-axis linkage robotic arm and a diamond grinding head. The grinding pressure control accuracy is ±0.1N, and the position repeatability accuracy is ±2. The adaptive PID controller interacts with the computing center (304) via a real-time Ethernet protocol.

Images