Mould precision injection molding machining method and device based on machine vision

Abstract

The invention relates to the technical field of mold processing, and provides a mold precision injection molding processing method and device based on machine vision, and the method comprises the following steps: carrying out all-directional scanning on the surface of a mold cavity based on a machine vision system to obtain cavity three-dimensional image data of the mold cavity; inputting the three-dimensional image data of the cavity into an image analysis and detection model to obtain a first analysis and detection result; calling a spectrum analyzer to detect the to-be-injection-molded material based on the first analysis detection result to obtain a material characteristic detection result of the to-be-injection-molded material; determining material processing parameters of the to-be-injection-molded material according to the material characteristic detection result, and melting the to-be-injection-molded material based on the material processing parameters to obtain a material melt; and first mold injection molding machining parameters are determined based on the mold characteristic parameters of the mold cavity, and the material melt is injected into the mold cavity based on the first mold injection molding machining parameters. The product quality stability and the production efficiency are improved, and the production cost is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of mold processing, and in particular to a mold precision injection molding method and a device thereof based on machine vision. Background Art

[0002] In the field of mold precision injection molding, traditional processing methods usually rely on preset process parameters and the experience of operators to control the injection molding process. First, the actual performance of the material may fluctuate between different batches, and the preset process parameters are difficult to dynamically adapt to such changes. Therefore, it is easy to cause unstable quality of injection molded products, such as dimensional deviation, surface defects and other problems. Secondly, the injection mold will wear and deform after long-term use. The traditional method cannot timely and accurately perceive the changes in these mold states and adjust the processing parameters accordingly, which further affects the accuracy and quality consistency of the product. Furthermore, for some complex structure molds and high-precision injection molding products, it is difficult for traditional processing methods to accurately control the melt flow behavior during the injection molding process, which may cause defects such as uneven filling and trapped air, reduce the product yield and increase production costs. In addition, traditional quality inspection mainly relies on sampling inspection, which is not only inefficient, but also unable to monitor the production process of each product in real time, and cannot timely discover and correct abnormal conditions in the production process. Once batch quality problems occur, it will cause large economic losses. Summary of the invention

[0003] The present invention provides a mold precision injection molding processing method and device based on machine vision, which are used to effectively overcome the defects of traditional processing methods through comprehensive and accurate monitoring of mold status, material properties, injection molding process and product quality, improve product quality stability, production efficiency and reduce production costs.

[0004] In a first aspect, the present invention provides a mold precision injection molding method based on machine vision, comprising: Performing an all-round scan on the surface of the mold cavity based on a machine vision system to obtain three-dimensional image data of the mold cavity; Inputting the cavity three-dimensional image data into an image analysis detection model to obtain a first analysis detection result output by the image analysis detection model; the image analysis detection model is trained based on sample image data and its corresponding analysis detection result labels; Based on the first analysis and detection result, a spectrum analyzer is called to detect the material to be injected, so as to obtain a material property detection result of the material to be injected; Determining material processing parameters of the material to be injected according to the material property detection result, and melting the material to be injected based on the material processing parameters to obtain a material melt; A first mold injection molding process parameter is determined based on the mold characteristic parameter of the mold cavity, and the material melt is injected into the mold cavity based on the first mold injection molding process parameter.

[0005] In a second aspect, the present invention provides a mold precision injection molding processing device based on machine vision, which is applied to the mold precision injection molding processing method based on machine vision as described in the first aspect; the mold precision injection molding processing device based on machine vision includes: An image acquisition module, used for performing an all-round scan on the surface of the mold cavity based on a machine vision system to obtain three-dimensional cavity image data of the mold cavity; A model detection module, used for inputting the cavity three-dimensional image data into an image analysis detection model to obtain a first analysis detection result output by the image analysis detection model; the image analysis detection model is trained based on sample image data and its corresponding analysis detection result label; A material detection module, configured to call a spectrum analyzer to detect the material to be injected based on the first analysis and detection result, and obtain a material property detection result of the material to be injected; A processing module, used for determining material processing parameters of the material to be injected according to the material property detection result, and melting the material to be injected based on the material processing parameters to obtain a material melt; The injection molding module is used to determine a first mold injection molding process parameter based on the mold characteristic parameter of the mold cavity, and to inject the material melt into the mold cavity based on the first mold injection molding process parameter.

[0006] In a third aspect, the present invention further provides an electronic device, comprising: a memory for storing a computer software program; a processor for reading and executing the computer software program, thereby implementing any of the above-mentioned machine vision-based mold precision injection molding methods.

[0007] In a fourth aspect, the present invention further provides a non-transitory computer-readable storage medium, wherein a computer software program is stored in the storage medium, and when the computer software program is executed by a processor, the machine vision-based mold precision injection molding processing method as described above is implemented.

[0008] In a fifth aspect, the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned machine vision-based mold precision injection molding methods.

[0009] The mold precision injection molding method based on machine vision provided by the embodiment of the present invention can detect the mold cavity accurately through the machine vision system in the mold state detection step, so as to timely discover and deal with potential problems of the mold, avoid product quality problems caused by mold defects, and ensure the stability of product appearance quality. The material property analysis step ensures that the injection molding parameters can be accurately adjusted according to the actual characteristics of the material, so that the differences between different batches of materials are effectively compensated, so that the fluidity, formability and other properties of the melt are more stable, and the product size deviation and internal defects caused by material fluctuations are reduced, thereby improving product quality. Since the mold state detection and material property analysis can be completed quickly before injection molding, and the injection molding parameters can be automatically optimized and adjusted, the number of mold trials and adjustment time caused by mold problems and material differences are reduced, the initial success rate of injection molding production is improved, the production cycle of the product is shortened, and the production efficiency is improved. The improvement of product quality stability reduces the generation rate of waste and defective products, reduces the waste of raw materials, and directly reduces production costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 It is a schematic flow chart of a mold precision injection molding method based on machine vision provided by an embodiment of the present invention; Figure 2 Schematic diagram of the structure of a mold precision injection molding device based on machine vision provided by an embodiment of the present invention; Figure 3 An embodiment diagram of an electronic device provided by an embodiment of the present invention; Figure 4 An embodiment diagram of a computer-readable storage medium provided for an embodiment of the present invention. DETAILED DESCRIPTION

[0011] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0012] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0013] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in the present invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present invention.

[0014] See also Figure 1 As shown, Figure 1 : is a flow chart of a mold precision injection molding method based on machine vision provided by the present invention. In the embodiment of the present invention, the execution subject of the mold precision injection molding method based on machine vision is an injection molding device. Therefore, the mold precision injection molding method based on machine vision includes: Step 10: Scan the surface of the mold cavity in all directions based on the machine vision system to obtain three-dimensional image data of the mold cavity.

[0015] Optionally, a machine vision system is installed in the injection molding device in an embodiment of the present invention, wherein the machine vision system includes multiple laser emitters and a high-resolution CCD camera. Therefore, the injection molding device can call multiple laser emitters and a high-resolution CCD camera to perform a full-range scan of the surface of the mold cavity to obtain three-dimensional cavity image data of the mold cavity, as specifically described in steps 101 to 103.

[0016] Step 20, input the cavity three-dimensional image data into the image analysis detection model to obtain the first analysis detection result output by the image analysis detection model.

[0017] Optionally, an image analysis and detection model is embedded in the injection molding device of the embodiment of the present invention, wherein the image analysis and detection model is trained based on sample image data and its corresponding analysis and detection result labels.

[0018] Therefore, the injection molding processing device inputs the cavity three-dimensional image data into the image analysis and detection model, and performs feature extraction and feature fusion on the cavity three-dimensional image data through the image analysis and detection model to obtain the first analysis and detection result output by the image analysis and detection model, as specifically described in steps 201 to 203.

[0019] Step 30: Based on the first analysis and detection result, a spectrum analyzer is called to detect the material to be injected, so as to obtain a material property detection result of the material to be injected.

[0020] Furthermore, the injection molding processing device identifies the first analysis test result to determine whether the first analysis test result meets the preset result, wherein the preset result may be, for example, that the degree of wear in the first analysis test result is greater than the preset degree of wear, or that the surface roughness in the first analysis test result is greater than the preset roughness.

[0021] Further, if it is determined that the first analysis test result meets the preset result, the injection molding processing device calls the spectrum analyzer to test the material to be injected to obtain the material property test result of the material to be injected, as described in steps 301 to 303.

[0022] Step 40 , determining material processing parameters of the material to be injected according to the material property detection result, and melting the material to be injected based on the material processing parameters to obtain a material melt.

[0023] Optionally, the material processing parameters in the embodiment of the present invention include melting temperature , screw speed , Backpressure Etc. Melting temperature For example, according to the crystallinity of the material , thermal conductivity and specific heat capacity In one embodiment, the ideal melting temperature range of the material is , determined using fuzzy logic control algorithm. Crystallinity The fuzzy set is {low, medium, high}, thermal conductivity The fuzzy set is {small, medium, large}, and the specific heat capacity The fuzzy set is {low, medium, high}, the melting temperature The fuzzy set is {low temperature, medium temperature, high temperature}. Create a fuzzy rule table, for example: if High and For small and If For high temperature; if For the middle For the middle For the middle, For medium temperature, etc. According to the fuzzy rules, in one embodiment, , , are the membership function values ​​of crystallinity, thermal conductivity and specific heat in their respective fuzzy sets. Fuzzy rules :if for and for and for ,but for , its activation intensity .

[0024] Final melting temperature The clarity value is calculated by the centroid method: ,in, For the The central value of the melting temperature fuzzy set corresponding to the fuzzy rule.

[0025] Optional, screw speed and backpressure The determination of is also based on a similar multi-factor comprehensive consideration algorithm, such as the melt index of the material. , material density In the melting process, the actual melting state of the material is monitored in real time by temperature sensors, pressure sensors, etc., and the PID control algorithm is used to adjust the heating power. and the speed of the screw drive motor To ensure that the material can stably melt to the target state. The PID control algorithm formula is: ,in, To control the output (such as heating power or motor speed adjustment), The deviation between the actual value and the target value (such as the actual temperature and the melting temperature ), , , They are proportional, integral, and differential coefficients, respectively, which can be adjusted through experiments or adaptive algorithms according to material properties and device characteristics.

[0026] Furthermore, the injection molding device melts the material to be injected according to the material processing parameters to obtain a material melt of the material to be injected.

[0027] Step 50 : determining first mold injection molding process parameters based on mold characteristic parameters of the mold cavity, and injecting material melt into the mold cavity based on the first mold injection molding process parameters.

[0028] Further, the injection molding device determines the first mold injection molding parameters according to the mold characteristic parameters of the mold cavity, as described in steps 501 to 505, and injects the material melt into the mold cavity according to the first mold injection molding parameters.

[0029] The embodiment of the present invention can detect the mold cavity accurately through the machine vision system, so as to timely discover and deal with potential problems of the mold, avoid product quality problems caused by mold defects, and ensure the stability of product appearance quality. On the other hand, it ensures that the injection molding parameters can be accurately adjusted according to the actual characteristics of the material, so that the differences between different batches of materials are effectively compensated, so that the fluidity, formability and other properties of the melt are more stable, and the product size deviation and internal defects caused by material fluctuations are reduced, thereby improving product quality. Since the mold state detection and material property analysis can be completed quickly before injection molding, and the injection molding parameters can be automatically optimized and adjusted, the number of mold trials and adjustment time caused by mold problems and material differences are reduced, the initial success rate of injection molding production is improved, the product production cycle is shortened, and the production efficiency is improved. The improvement of product quality stability reduces the generation rate of waste and defective products, reduces the waste of raw materials, and directly reduces production costs.

[0030] In one embodiment, the description of steps 101 to 103 is as follows: Step 101, obtaining the angle between the laser emitter and the surface of the mold cavity , the angle between the high-resolution CCD camera and the laser beam emitted by the laser transmitter , the displacement of the laser spot formed by the laser on the surface of the mold cavity on the imaging plane of the high-resolution CCD camera , focal length of high-resolution CCD camera ; Step 102, based on the angle , Angle , displacement and focal length , determine the height of any point on the surface of the mold cavity ,high The calculation formula is ; Step 103, processing and splicing the images of the surface of the mold cavity at multiple viewing angles captured by the high-resolution CCD camera, calculating the surface height information of the mold cavity corresponding to each pixel point, and constructing the cavity three-dimensional image data of the mold cavity.

[0031] Specifically, the embodiment of the present invention adopts a multi-view laser triangulation method, that is, multiple laser emitters and corresponding high-resolution CCD cameras are arranged around the mold cavity. The laser emitter emits a laser beam to the surface of the mold cavity at a specific angle, and the laser forms a light spot on the surface of the mold cavity. Due to the height change of the surface of the mold cavity, the angle of the reflected light will also change. The high-resolution CCD camera captures images of the reflected light from different perspectives.

[0032] In one embodiment, the angle between the laser emitter and the surface of the mold cavity is , the angle between the high-resolution CCD camera and the laser beam is , the displacement of the laser spot on the imaging plane of the high-resolution CCD camera is , the focal length of the high-resolution CCD camera is According to the principle of similar triangles, the height of a certain point on the surface of the mold cavity can be deduced Calculation formula: .

[0033] By processing and splicing images from multiple perspectives, the surface height information of the mold cavity corresponding to each pixel is calculated in combination with the above formula, thereby constructing the three-dimensional image data of the cavity. The image at each viewing angle has pixel coordinates The corresponding height is ,go through After processing the viewing angles, the final cavity 3D image data ,in, For the The weight coefficient of each perspective can be dynamically adjusted according to the importance and accuracy of the perspective, for example , For the The angle between a viewing angle and the center axis of the cavity.

[0034] The embodiment of the present invention uses a machine vision system to accurately detect the mold cavity, timely discover potential problems with the mold, avoid product quality problems caused by mold defects, and ensure the stability of product appearance quality.

[0035] In one embodiment, the description of steps 201 to 203 is as follows: Step 201, inputting the three-dimensional image data of the cavity into the image analysis detection model, performing feature extraction on the three-dimensional image data of the cavity based on the deep convolutional neural network layer in the image analysis detection model, and obtaining local features of the cavity; Step 202, extracting features from the three-dimensional image data of the cavity based on the graph neural network layer in the image analysis detection model to obtain the topological structure features of the cavity; Step 203, based on the fully connected layer in the image analysis detection model, the local features of the cavity and the topological structure features of the cavity are connected to obtain the first analysis and detection result output by the image analysis detection model.

[0036] Optionally, the embodiment of the present invention adopts a structure combining a deep convolutional neural network (DCNN) and a graph neural network (GNN). The three-dimensional image data of the cavity is input into the image analysis and detection model, and the deep convolutional neural network layer DCNN in the image analysis and detection model extracts features from the three-dimensional image data of the cavity to obtain local features of the cavity in the three-dimensional image data, such as surface texture, tiny defects, etc. The convolution kernel size of the layer is , the step length is , the number of input channels is , the number of output channels is , then the output feature map size of this layer ,in, is the input feature map size, To fill the size, each element of the feature map is: .

[0037] in, For the The convolution kernel of the layer, For the The bias term of the layer.

[0038] Furthermore, based on the graph neural network layer GNN in the image analysis detection model, feature extraction is performed on the three-dimensional image data of the cavity, such as analyzing the overall topological structure of the cavity to obtain the cavity topological structure features, such as detecting the connectivity and complex contour features of the mold cavity. In one embodiment, the surface of the mold cavity is discretized into Nodes , the edge set is , the information transfer formula of GNN is: .

[0039] in, For Node In the The eigenvector of the iteration, For Node The set of neighbor nodes of and is the learnable weight matrix, is the activation function (such as ReLU function), is the bias vector.

[0040] The training process of the image analysis and detection model in the embodiment of the present invention adopts the back propagation algorithm, and the loss function is: ,in, is the number of training samples, is the true label, For the model prediction results, is the regularization coefficient, For model The weight elements of the layer minimize the loss function by continuously adjusting the network parameters.

[0041] Furthermore, based on the fully connected layer in the image analysis detection model, the local features of the cavity and the topological structure features of the cavity are connected to obtain a first analysis detection result, wherein the first analysis detection result in the embodiment of the present invention includes the wear degree of the mold cavity , surface roughness , whether there is foreign matter attached For example, the degree of wear It can be obtained by calculating the volume loss of the key part of the cavity. In one embodiment, the original volume of the key part is , the current volume is ,but , the wear degree prediction value output by the model It is calculated based on the features extracted by the above DCNN and GNN through the fully connected layer: .

[0042] in, and are the wear-related feature vectors extracted by DCNN and GNN respectively. , is the weight parameter, is the bias term.

[0043] The embodiment of the present invention can accurately obtain analysis and detection results through the image analysis detection model, so that mold precision injection molding can be performed based on the analysis and detection results, thereby improving the stability of product quality.

[0044] In one embodiment, the description of steps 301 to 303 is as follows: Step 301, if it is determined based on the first analysis and detection result that the surface of the mold cavity meets the preset result, then call the spectrum analyzer to emit multiple light bands to detect the material to be injected, and obtain the reflectivity, absorptivity and transmittance of the material to be injected for each light band emitted by the spectrum analyzer; Step 302, establishing a relationship model between the material properties of the material to be injected and the light band of the spectrum analyzer based on the reflectivity, absorptivity and transmittance of the material to be injected to each light band emitted by the spectrum analyzer; Step 303: Analyze the relationship model to obtain the material property detection result of the material to be injected.

[0045] Optionally, if it is determined based on the first analysis test result that the surface of the mold cavity does not meet the preset result, wherein the preset result is such as the wear degree in the first analysis test result is greater than the preset wear degree, and the surface roughness in the first analysis test result is greater than the preset roughness, the detection parameters of the spectrometer are adjusted according to the first analysis test result of the mold cavity. For example, if the wear degree of the mold cavity is high or the surface roughness is large, it may affect the flow and molding of the material in the cavity. At this time, the spectrometer will increase the detection accuracy of the viscosity-related properties of the material. In one embodiment, the mold cavity wear degree threshold is ,when When the spectrum analyzer detects the material viscosity coefficient, the detection accuracy is increased by times ( ).

[0046] If it is determined based on the first analysis and detection result that the surface of the mold cavity meets the preset result, the spectrometer is called to emit multiple light bands to detect the material to be injected. The spectrometer in the embodiment of the present invention adopts multi-band spectral analysis technology to emit multiple bands of light from ultraviolet to infrared to illuminate the material to be injected, and detects the absorption, reflection and transmission characteristics of the material to light of different bands, and obtains the reflectivity, absorption and transmittance of the material to be injected for each light band emitted by the spectrometer. In one embodiment, the light band emitted by the spectrometer is , materials for The reflectivity of the light in this band is The absorption rate is , the transmittance is ,satisfy .

[0047] Furthermore, a relationship model between the material properties of the material to be injected and the light bands of the spectrometer is established by measuring the reflectivity, absorptivity and transmittance of the material to be injected for each light band emitted by the spectrometer, and the relationship model is analyzed to obtain the material property detection results of the material to be injected, wherein the material property detection results include material composition information, material purity information and material physical property parameters. In one embodiment, for the crystallinity of the material , using an algorithm combining multiple linear regression and neural network: .

[0048] in, is the linear regression coefficient; is a small neural network used to capture the nonlinear relationship between spectral data; is the weight coefficient of the neural network, is the bias term. The structure of the neural network can be a simple multi-layer perceptron, such as the input layer is nodes (corresponding to The reflectivity of the band), the hidden layer has nodes, the output layer is 1 node (corresponding to the predicted value of crystallinity), and the activation function of the hidden layer can be the Sigmoid function , the calculation formula of the output layer is: .

[0049] in, , , is the weight parameter of the neural network, , is the bias term.

[0050] The embodiments of the present invention ensure that the injection molding parameters can be accurately adjusted according to the actual characteristics of the material, so that the differences between different batches of materials are effectively compensated, the fluidity, formability and other properties of the melt are more stable, the product dimensional deviation and internal defects caused by material fluctuations are reduced, and the product quality is improved.

[0051] In one embodiment, the description of steps 501 to 505 is as follows: Step 501, obtaining the temperature variation range of the mold cavity during the injection molding process, and the heat exchange rate between the mold cavity and the surrounding environment; Step 502, calculating the thermal equilibrium time based on the temperature variation range, the heat exchange rate and the heat capacity, and determining the injection cycle of the mold cavity based on the thermal equilibrium time; Step 503, determining the injection speed of the mold cavity based on the filling volume and the injection cycle; Step 504, determining the injection pressure of the mold cavity based on the minimum wall thickness and the injection speed; Step 505, determining the injection cycle, injection speed and injection pressure as the first mold injection molding processing parameters.

[0052] Optionally, mold characteristic parameters include the heat capacity of the mold , cooling channel structure parameters of the mold (such as channel diameter , length of waterway , water channel spacing etc.), thermal conductivity of mold material wait.

[0053] First calculate the thermal equilibrium time of the mold , a simplified model using the finite element thermal analysis algorithm: ,in, is the temperature variation range of the mold during the injection molding process, The heat exchange rate between the mold and the surrounding environment: (in, is the length of different parts of the mold, , is the diameter or thickness of the adjacent two-layer mold structure, is the temperature of the corresponding part, is the ambient temperature. According to the thermal equilibrium time of the mold Determine the injection cycle ,For example ,in, This is the safety margin time.

[0054] Furthermore, the injection pressure Determination of the complexity of the mold cavity (which can be quantified by factors such as the surface area to volume ratio of the cavity, the number of parting surfaces, etc.), the viscosity of the material melt and injection speed . The method combining empirical formula and numerical simulation is adopted: ,in, is the flow path length of the melt in the cavity, is the minimum wall thickness of the cavity, is the basic injection pressure, It is an empirical coefficient (determined according to different materials and mold types).

[0055] Furthermore, the injection speed According to the filling volume of the mold cavity , the flow rate of the material melt and injection time ( Injection cycle The injection stage time in the process is determined by: , where the flow rate of the material melt is According to the screw diameter , screw speed and the compression ratio of the melt calculate: .

[0056] Furthermore, the holding pressure And holding time According to the shrinkage rate of the material , the volume of the mold cavity The PVT model is first established based on the PVT data of the material. Then, during the pressure holding stage, the pressure holding pressure and time are calculated according to the shrinkage of the material. For example, in one embodiment, the volume change of the material during the pressure holding stage is: , then the holding pressure ( is the pressure-volume coefficient calculated according to the PVT model), holding time According to the curing time of the material and the decay characteristics of the holding pressure, e.g. ( is the attenuation coefficient, determined according to the material and mold characteristics).

[0057] Furthermore, during the injection molding process, pressure sensors, displacement sensors, etc. are used to monitor the pressure, melt flow position and other parameters in real time during the injection molding process, and an adaptive control algorithm is used to dynamically adjust the injection molding parameters. For example, if the injection molding pressure exceeds the preset upper limit, , then reduce the injection speed appropriately , the adjustment formula is At the same time, the injection cycle and holding pressure parameters are recalculated according to the new injection speed to ensure the stability of the injection process and the consistency of product quality.

[0058] In the embodiment of the present invention, since mold state detection and material property analysis can be completed quickly before injection molding, and injection molding parameters can be automatically optimized and adjusted, the number of mold trials and adjustment time caused by mold problems and material differences are reduced, the initial success rate of injection molding production is improved, the production cycle of the product is shortened, and production efficiency is improved. The improvement of product quality stability reduces the generation rate of waste and defective products, reduces the waste of raw materials, and directly reduces production costs.

[0059] In one embodiment, the mold precision injection molding method based on machine vision also includes: Step a1, during the process of injecting the material melt into the mold cavity with the first mold injection molding process parameters, monitor the flow state information of the material melt in the mold cavity; step a2, based on the flow state information, adjust the first mold injection molding process parameters to obtain the second mold injection molding process parameters; step a3, based on the second mold injection molding process parameters, inject the material melt into the mold cavity.

[0060] Optionally, the flow state information in the embodiment of the present invention includes the melt front position, melt flow rate and melt filling uniformity. Therefore, in the process of injecting the material melt into the mold cavity with the first mold injection molding processing parameters, the melt front position, melt flow rate and melt filling uniformity of the material melt in the mold cavity are monitored.

[0061] In one embodiment, the monitoring of the melt front position is as follows: The machine vision system is used to take real-time photos of the inside of the mold cavity. Multiple marking points are pre-set inside the mold cavity (these marking points can be tiny reflective or fluorescent material points, which do not affect injection molding), and the position of the melt front is determined by identifying the relative position of the marking points and the melt front in the image.

[0062] In one embodiment, the image resolution captured by the machine vision system is pixels. , the coordinates of the marker points in the image are , determine the coordinates of multiple feature points on the melt front profile through image recognition algorithm .

[0063] Calculate the distance from the melt front to the marked point , using a calculation method based on pixel distance: ,in, is the ratio coefficient between image pixels and actual size, obtained through pre-calibration.

[0064] Then, based on the distance information of multiple feature points, the overall position distribution of the melt front is determined, for example, by calculating the average value of these distances and standard deviation To evaluate the concentration and dispersion of the melt front position.

[0065] In one embodiment, the melt flow rate monitoring is as follows: The time series image analysis method is used. Multiple frames of images of the inside of the mold cavity are taken to compare the changes in the position of the melt front in different frames.

[0066] In one embodiment, The coordinates of the characteristic point of the melt front at time , No. The coordinates corresponding to the time are .

[0067] The flow velocity of the melt in the direction of the characteristic point is .

[0068] For the entire melt front, after calculating the flow velocities of multiple characteristic points, the average flow velocity of the melt is determined by the weighted average method. ,in, is the weight coefficient of the feature point, which can be determined according to the importance of the location of the feature point to the overall flow. For example, the feature point near the gate has a larger weight, so ( to a minimum value to prevent the denominator from being zero).

[0069] In one embodiment, the melt filling uniformity monitoring is specifically as follows: Divide the mold cavity into sub-areas , the filling height of the melt in each sub-area is analyzed by a machine vision system In one embodiment, the gray value of the melt filling area in the image has a functional relationship with the filling height. (in, For sub-region The average gray value of the melt filling area inside the sample is obtained by pre-experimental calibration, for example, by using polynomial fitting. ( is the fitting coefficient). Calculate the filling uniformity index ,in, , Smaller values ​​mean more uniform filling.

[0070] Further, the injection molding process parameters of the first mold are adjusted based on the flow state information to obtain the injection molding process parameters of the second mold, wherein the injection molding process parameters of the second mold include injection pressure adjustment, injection speed adjustment and holding pressure parameter adjustment.

[0071] In one embodiment, the specific process for adjusting the injection pressure is as follows: When the melt front position deviates far from the expected position (such as the average distance Greater than the preset threshold ) or uneven flow velocity (such as velocity standard deviation Greater than ), the injection pressure needs to be adjusted.

[0072] In one embodiment, the initial injection pressure is , adjusted injection pressure Adopts an adjustment algorithm based on fuzzy logic. Defines the melt front position deviation ( The fuzzy set of the ideal melt front position is {negative large, negative medium, negative small, zero, positive small, positive medium, positive large}, and the flow velocity deviation ( The fuzzy set of the ideal flow velocity standard deviation is {negative large, negative medium, negative small, zero, positive small, positive medium, positive large}, and the injection pressure adjustment amount The fuzzy set of is {substantially decrease, moderately decrease, slightly decrease, unchanged, slightly increase, moderately increase, substantially increase}.

[0073] Create a fuzzy rule table, for example: if Negative and large If is negative, For a substantial increase; if is positive and small If is zero, For a small increase, etc.

[0074] Inference is performed based on fuzzy rules. In one embodiment, , are the membership function values ​​of melt front position deviation and flow velocity deviation in their respective fuzzy sets. Fuzzy rules :if for and for ,but for , its activation intensity .

[0075] The final clear value of the injection pressure adjustment is calculated by the center of gravity method: ,in, For the The central value of the fuzzy set of injection pressure adjustment corresponding to the fuzzy rule.

[0076] The adjusted injection pressure .

[0077] In one embodiment, the specific process for adjusting the injection speed is as follows: When the melt filling uniformity is poor (such as Greater than ), the injection speed is adjusted. In one embodiment, the initial injection speed is , adjusted injection speed .

[0078] Adopting the adjustment algorithm based on neural network. , thermal equilibrium parameters of the mold cavity (such as temperature differences in different parts of the cavity), the current viscosity of the material melt As the input of the neural network. The neural network structure is a multi-layer perceptron, with 3 nodes in the input layer and 1 node in the hidden layer. There are nodes, and the output layer is 1 node (corresponding to the injection speed adjustment ratio ). The activation function of the hidden layer uses the hyperbolic tangent function , the calculation formula of the output layer is: ,in, For input parameters , , , , , is the weight parameter of the neural network, , is the bias term).

[0079] The adjusted injection speed .

[0080] In one embodiment, the specific process for adjusting the pressure holding parameters is as follows: If the melt shrinkage is found to be inconsistent with expectations during the injection molding process (such as by monitoring the pressure changes inside the mold cavity and the melt volume changes), adjust the holding pressure and holding time.

[0081] In one embodiment, the initial holding pressure is The initial holding time is , after adjusting the holding pressure And holding time .

[0082] First calculate the actual shrinkage of the melt (in, is the theoretical volume of the melt when injection molding is completed, is the actual monitored melt volume).

[0083] The holding pressure is adjusted using a proportional control algorithm: .

[0084] The holding time adjustment uses an algorithm based on an exponential function: ,in, It is an exponential coefficient determined according to the curing characteristics of the material and the thermal characteristics of the mold.

[0085] Further, the material melt is injected into the mold cavity according to the injection molding processing parameters of the second mold, that is, according to the adjusted injection molding processing parameters of the second mold (including , , , During the injection molding process, the flow state information of the melt is continuously monitored, and the above parameter adjustment steps are repeated until the injection molding process is completed to ensure that the flow state of the material melt in the mold cavity is always in a relatively ideal state during the entire injection molding process, thereby improving the quality and consistency of the injection molded products.

[0086] In one embodiment, the mold precision injection molding processing method based on machine vision also includes: after the mold injection is completed and before the product is demolded, the mold injection product is fully inspected by the machine vision system to obtain the product three-dimensional image data of the mold injection product, and the product three-dimensional image data is input into the image analysis detection model to obtain the second analysis detection result output by the image analysis detection model, such as the process of step 10 to step 20, which will not be repeated here. Further, if it is determined that the second analysis detection result meets the preset result, the mold injection product is demolded.

[0087] The embodiment of the present invention performs a comprehensive inspection on the product before demoulding, and can timely discover and remove unqualified products, thereby avoiding mixing defective products into qualified products and ensuring the stability and reliability of product quality.

[0088] Furthermore, the mold precision injection molding processing system based on machine vision provided by the present invention is described below. The mold precision injection molding processing system based on machine vision described below and the mold precision injection molding processing method based on machine vision described above can be referenced to each other.

[0089] Optional, see Figure 2 , Figure 2 : is a structural schematic diagram of a mold precision injection molding processing device based on machine vision provided by the present invention, and the mold precision injection molding processing device based on machine vision includes: An image acquisition module 210 is used to perform an all-round scan on the surface of the mold cavity based on a machine vision system to obtain three-dimensional image data of the mold cavity; The model detection module 220 is used to input the cavity three-dimensional image data into the image analysis detection model to obtain the first analysis detection result output by the image analysis detection model; the image analysis detection model is trained based on the sample image data and its corresponding analysis detection result label; A material detection module 230, configured to call a spectrum analyzer to detect the material to be injected based on the first analysis detection result, and obtain a material property detection result of the material to be injected; A processing module 240 is used to determine material processing parameters of the material to be injected according to the material property detection result, and melt the material to be injected based on the material processing parameters to obtain a material melt; The injection molding module 250 is used to determine the first mold injection molding process parameters based on the mold characteristic parameters of the mold cavity, and to inject the material melt into the mold cavity based on the first mold injection molding process parameters.

[0090] In the mold state detection step of the embodiment of the present invention, the accurate detection of the mold cavity by the machine vision system can timely discover and deal with potential problems of the mold, avoid product quality problems caused by mold defects, and ensure the stability of product appearance quality. The material property analysis step ensures that the injection molding parameters can be accurately adjusted according to the actual characteristics of the material, so that the differences between different batches of materials are effectively compensated, so that the fluidity, formability and other properties of the melt are more stable, and the product size deviation and internal defects caused by material fluctuations are reduced, thereby improving product quality. Since the mold state detection and material property analysis can be completed quickly before injection molding, and the injection molding parameters can be automatically optimized and adjusted, the number of mold trials and adjustment time caused by mold problems and material differences are reduced, the initial success rate of injection molding production is improved, the product production cycle is shortened, and the production efficiency is improved. The improvement of product quality stability reduces the generation rate of waste and defective products, reduces the waste of raw materials, and directly reduces production costs.

[0091] See also Figure 3 , Figure 3 FIG. 1 is an embodiment diagram of an electronic device provided by an embodiment of the present invention. Figure 3 As shown, an embodiment of the present invention provides an electronic device 300, including a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and executable on the processor 320. When the processor 320 executes the computer program 311, the following steps are implemented: The surface of the mold cavity is scanned in all directions based on the machine vision system to obtain the three-dimensional image data of the mold cavity; Inputting the cavity three-dimensional image data into the image analysis detection model to obtain a first analysis detection result output by the image analysis detection model; the image analysis detection model is trained based on the sample image data and its corresponding analysis detection result label; Based on the first analysis and detection result, a spectrum analyzer is called to detect the material to be injected, so as to obtain a material property detection result of the material to be injected; Determining material processing parameters of the material to be injected according to the material property test results, and melting the material to be injected based on the material processing parameters to obtain a material melt; A first mold injection molding process parameter is determined based on the mold characteristic parameter of the mold cavity, and the material melt is injected into the mold cavity based on the first mold injection molding process parameter.

[0092] See also Figure 4 , Figure 4 Detailed description of an embodiment of a computer-readable storage medium provided by an embodiment of the present invention. Figure 4As shown, this embodiment provides a computer-readable storage medium 400, on which a computer program 311 is stored. When the computer program 311 is executed by a processor, the following steps are implemented: The surface of the mold cavity is scanned in all directions based on the machine vision system to obtain the three-dimensional image data of the mold cavity; Inputting the cavity three-dimensional image data into the image analysis detection model to obtain a first analysis detection result output by the image analysis detection model; the image analysis detection model is trained based on the sample image data and its corresponding analysis detection result label; Based on the first analysis and detection result, a spectrum analyzer is called to detect the material to be injected, so as to obtain a material property detection result of the material to be injected; Determining material processing parameters of the material to be injected according to the material property test results, and melting the material to be injected based on the material processing parameters to obtain a material melt; A first mold injection molding process parameter is determined based on the mold characteristic parameter of the mold cavity, and the material melt is injected into the mold cavity based on the first mold injection molding process parameter.

[0093] On the other hand, the present invention further provides a computer program product, which includes a computer program. The computer program can be stored in a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the mold precision injection molding method based on machine vision provided by the above methods, and the method includes: The surface of the mold cavity is scanned in all directions based on the machine vision system to obtain the three-dimensional image data of the mold cavity; Inputting the cavity three-dimensional image data into the image analysis detection model to obtain a first analysis detection result output by the image analysis detection model; the image analysis detection model is trained based on the sample image data and its corresponding analysis detection result label; Based on the first analysis and detection result, a spectrum analyzer is called to detect the material to be injected, so as to obtain a material property detection result of the material to be injected; Determining material processing parameters of the material to be injected according to the material property test results, and melting the material to be injected based on the material processing parameters to obtain a material melt; A first mold injection molding process parameter is determined based on the mold characteristic parameter of the mold cavity, and the material melt is injected into the mold cavity based on the first mold injection molding process parameter.

[0094] The system embodiment described above is merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art may understand and implement it without creative work.

[0095] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0096] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A mold precision injection molding method based on machine vision, characterized in that: include: Performing an all-round scan on the surface of the mold cavity based on a machine vision system to obtain three-dimensional image data of the mold cavity; Inputting the cavity three-dimensional image data into an image analysis detection model to obtain a first analysis detection result output by the image analysis detection model; the image analysis detection model is trained based on sample image data and its corresponding analysis detection result labels; Based on the first analysis and detection result, a spectrum analyzer is called to detect the material to be injected, so as to obtain a material property detection result of the material to be injected; Determining material processing parameters of the material to be injected according to the material property detection result, and melting the material to be injected based on the material processing parameters to obtain a material melt; A first mold injection molding process parameter is determined based on the mold characteristic parameter of the mold cavity, and the material melt is injected into the mold cavity based on the first mold injection molding process parameter.

2. The mold precision injection molding method based on machine vision according to claim 1 is characterized in that: The mold characteristic parameters include the heat capacity, water channel diameter, water channel length and water channel spacing of the mold, and the material thermal conductivity, filling volume and minimum wall thickness of the mold cavity; the first mold injection molding processing parameters are determined based on the mold characteristic parameters of the mold cavity, including: Obtaining a temperature variation range of the mold cavity during the injection molding process, and a heat exchange rate between the mold cavity and the surrounding environment; Calculating a thermal equilibrium time based on the temperature variation range, the heat exchange rate and the heat capacity, and determining an injection cycle of the mold cavity based on the thermal equilibrium time; Determining an injection speed of the mold cavity based on the filling volume and the injection cycle; Determining an injection pressure of the mold cavity based on the minimum wall thickness and the injection speed; The injection molding cycle, the injection molding speed and the injection molding pressure are determined as the first mold injection molding processing parameters.

3. The mold precision injection molding method based on machine vision according to claim 1 is characterized in that: The step of inputting the cavity three-dimensional image data into an image analysis detection model to obtain a first analysis detection result output by the image analysis detection model includes: Inputting the cavity three-dimensional image data into the image analysis and detection model, performing feature extraction on the cavity three-dimensional image data based on the deep convolutional neural network layer in the image analysis and detection model to obtain local features of the cavity; Based on the graph neural network layer in the image analysis and detection model, feature extraction is performed on the three-dimensional image data of the cavity to obtain the topological structure features of the cavity; The local features of the cavity and the topological structure features of the cavity are connected based on the fully connected layer in the image analysis and detection model to obtain a first analysis and detection result output by the image analysis and detection model.

4. The mold precision injection molding method based on machine vision according to claim 1, characterized in that: The calling of a spectrum analyzer to detect the material to be injected based on the first analysis and detection result to obtain a material property detection result of the material to be injected includes: If it is determined based on the first analysis and detection result that the surface of the mold cavity meets the preset result, calling the spectrum analyzer to emit multiple light bands to detect the material to be injected, and obtaining the reflectivity, absorptivity and transmittance of the material to be injected for each light band emitted by the spectrum analyzer; Establishing a relationship model between the material properties of the material to be injected and the light band of the spectrum analyzer based on the reflectivity, absorptivity and transmittance of the material to be injected to each light band emitted by the spectrum analyzer; The relationship model is analyzed to obtain a material property detection result of the material to be injected; the material property detection result includes material composition information, material purity information and material physical property parameters.

5. The method for precision mold injection molding based on machine vision according to claim 1, characterized in that: The machine vision system includes a plurality of laser emitters and a high-resolution CCD camera; The machine vision system is used to perform an omnidirectional scan on the surface of the mold cavity to obtain the three-dimensional image data of the mold cavity, including: Obtaining the angle between the laser emitter and the surface of the mold cavity , the angle between the high-resolution CCD camera and the laser beam emitted by the laser emitter , the displacement of the laser spot formed by the laser on the surface of the mold cavity on the imaging plane of the high-resolution CCD camera , the focal length of the high-resolution CCD camera ; Based on the angle , the angle , the displacement and the focal length , determine the height of any point on the surface of the mold cavity ,high The calculation formula is ; The images of the surface of the mold cavity at multiple viewing angles captured by the high-resolution CCD camera are processed and spliced, the surface height information of the mold cavity corresponding to each pixel is calculated, and the cavity three-dimensional image data of the mold cavity is constructed.

6. The mold precision injection molding method based on machine vision according to any one of claims 1 to 5, characterized in that: The method further comprises: In the process of injecting the material melt into the mold cavity with the first mold injection molding processing parameters, monitoring the flow state information of the material melt in the mold cavity; the flow state information includes the melt front position, melt flow speed and melt filling uniformity; Adjusting the first mold injection molding process parameters based on the flow state information to obtain the second mold injection molding process parameters; The material melt is injected into the mold cavity based on the second mold injection molding process parameters.

7. The mold precision injection molding method based on machine vision according to any one of claims 1 to 5, characterized in that: The method further comprises: After the mold injection is completed and before the product is demolded, the mold injection product is comprehensively inspected based on the machine vision system to obtain product three-dimensional image data of the mold injection product; Inputting the product three-dimensional image data into the image analysis and detection model to obtain a second analysis and detection result output by the image analysis and detection model; The molded product is demolded based on the second analysis and detection result.

8. A mold precision injection molding processing device based on machine vision, characterized in that: Applicable to the mold precision injection molding method based on machine vision as described in any one of claims 1 to 7; the mold precision injection molding device based on machine vision comprises: An image acquisition module, used for performing an all-round scan on the surface of the mold cavity based on a machine vision system to obtain three-dimensional cavity image data of the mold cavity; A model detection module, used for inputting the cavity three-dimensional image data into an image analysis detection model to obtain a first analysis detection result output by the image analysis detection model; the image analysis detection model is trained based on sample image data and its corresponding analysis detection result label; A material detection module, configured to call a spectrum analyzer to detect the material to be injected based on the first analysis and detection result, and obtain a material property detection result of the material to be injected; A processing module, used for determining material processing parameters of the material to be injected according to the material property detection result, and melting the material to be injected based on the material processing parameters to obtain a material melt; The injection molding module is used to determine a first mold injection molding process parameter based on the mold characteristic parameter of the mold cavity, and to inject the material melt into the mold cavity based on the first mold injection molding process parameter.

9. An electronic device, comprising: Memory for storing computer software programs; A processor is used to read and execute the computer software program, wherein when the processor executes the computer software program, it implements the mold precision injection molding method based on machine vision as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium, wherein a computer software program is stored in the non-transitory computer-readable storage medium, and when the computer software program is executed by a processor, the mold precision injection molding processing method based on machine vision as described in any one of claims 1 to 7 is implemented.

Images