Forming process management and control method and system for anti-corrosion helical blade wear-resistant block

Abstract

The invention belongs to the field of forming processes, and provides a forming process management and control method and system for an anti-corrosion helical blade wear-resistant block, and the method comprises the steps: obtaining system pressure data and in-mold pressure data in real time, the system pressure data being obtained by a pressure sensor installed on an ejector of a forming machine, and the in-mold pressure data being obtained by a pressure sensor installed on an ejector of the forming machine; the in-mold pressure data is obtained by a plurality of pressure sensors mounted in the mold; based on the system pressure data and the in-mold pressure data, a pressure maintaining index, a peak pressure index, a residual pressure drop index and a pressure integral index are calculated, the pressure maintaining index is the average pressure of the mold in the pressure maintaining stage, and the peak pressure index is the maximum pressure of the mold in the compression stage; the residual pressure drop index is the average drop amount of the mold in the cooling stage, and the pressure integral index is the integral of the pressure curve of the mold in the forming period along with the time change, predicting the forming quality of the product in the mold based on the MLP model, and adjusting the process parameters of a forming machine when the predicted product quality has deviation. The deviation is eliminated; the forming machine can solve the quality problem of a forming machine in the prior art in the process of producing wear-resistant blocks.

Description

Technical Field

[0001] The present invention relates to the field of forming technology, and in particular to a forming technology control method and system for a corrosion-resistant spiral blade wear-resistant block. Background Art

[0002] Anti-corrosion spiral blade wear block is a kind of wear-resistant material designed to improve the service life and working efficiency of spiral blades. Its main function is to resist corrosion, wear and other adverse working conditions. It is widely used in industries such as petroleum, chemical industry, mining, etc., especially in shield machines that need to run for a long time.

[0003] In the production of existing corrosion-resistant and wear-resistant blocks, alloy powder and specific polymer powder are melted in a certain proportion, sprayed into the mold by a molding machine, and solidified after cooling. In the molding process, the selection of control parameters is crucial to the quality of the final molded parts. Traditional processes mainly rely on the process parameters of the molding machine, such as injection pressure, injection speed, mold temperature and cooling time. However, these traditional process parameters often cannot fully reflect the influencing factors such as the flow behavior of the polymer melt and material shrinkage, which leads to quality fluctuations of the molded parts and even defects, such as unstable geometric dimensions, surface defects, warping, etc. Summary of the invention

[0004] In view of the above technical problems, the present invention provides a forming process control method and system for corrosion-resistant spiral blade wear-resistant blocks to solve the quality problems existing in the forming machine in the production of wear-resistant blocks in the prior art.

[0005] Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by the practice of the present disclosure.

[0006] According to one aspect of the present invention, a method for controlling the forming process of a corrosion-resistant spiral blade wear block is disclosed, the method comprising: Real-time acquisition of system pressure data and in-mold pressure data, wherein the system pressure data is obtained by a pressure sensor installed on an ejector of a molding machine, and the in-mold pressure data is obtained by a plurality of pressure sensors installed in the mold, wherein the in-mold pressure data and the system pressure data include a pressure curve of the mold during a molding cycle, wherein the molding cycle includes filling, compression, pressure holding and cooling stages, and the positions of the plurality of pressure sensors in the mold include at least the gate, the front and rear of the gate, the center of the cavity, and an end point away from the gate; Based on the system pressure data and the in-mold pressure data, the pressure holding index, peak pressure index, residual pressure drop index, and pressure integral index are calculated, wherein the pressure holding index is the average pressure of the mold in the pressure holding stage, the peak pressure index is the maximum pressure of the mold in the compression stage, the residual pressure drop index is the average drop of the mold in the cooling stage, and the pressure integral index is the integral of the pressure curve of the mold in the forming cycle over time. After the pressure holding index, the peak pressure index, the residual pressure drop index, and the pressure integral index are normalized, they are input into the pre-trained MLP model to predict the forming quality of the product in the mold. When there is a deviation in the predicted product quality, the process parameters of the molding machine are adjusted until the deviation is eliminated.

[0007] Furthermore, the pressure holding index is calculated as follows: , and is the start and end time of the pressure holding phase, is the pressure curve of the system pressure data.

[0008] Furthermore, the pressure integral index is calculated as follows: , and is the start and end time of the forming cycle, is the pressure curve of the system pressure data.

[0009] Furthermore, the peak pressure index is calculated as follows: , is the pressure curve of the in-mold pressure data.

[0010] Furthermore, the calculation formula of the residual pressure drop index is: , and are the start and end time of the cooling phase, It is a pressure curve generated by two pressure sensors installed at the center of the cavity and two pressure sensors installed at the end points away from the gate in the system pressure data.

[0011] Furthermore, the MLP model, when trained, includes: The pressure holding index, peak pressure index, residual pressure drop index and pressure integral index calculated during the production of the product are collected and normalized to the range of 0-1 to obtain input training data; Collecting product quality classification results corresponding to the input training data as training labels; Construct a multilayer perceptron neural network model, the multilayer perceptron neural network model includes an input layer, a hidden layer, and an output layer, the input layer is used to receive the input training data, the hidden layer is used to perform weighted summation on the input training data based on a nonlinear activation function, and the number of nodes is multiple times that of the input layer, and the output layer uses a Sigmoid activation function to perform activation processing based on the properties of product quality to obtain a pre-output result; The difference between the pre-output result and the training label is calculated based on a binary cross entropy loss function, and the weights and biases of the model are updated by a gradient descent algorithm according to the calculated difference.

[0012] According to another aspect of the present invention, a forming process control system for a corrosion-resistant spiral blade wear-resistant block is disclosed, the system comprising: A data acquisition module, used for acquiring system pressure data and in-mold pressure data in real time, wherein the system pressure data is obtained by a pressure sensor installed on an ejector of the molding machine, and the in-mold pressure data is obtained by multiple pressure sensors installed in the mold, wherein the in-mold pressure data and the system pressure data include a pressure curve of the mold during a molding cycle, wherein the molding cycle includes filling, compression, pressure holding and cooling stages, and the positions of the multiple pressure sensors in the mold include at least the gate, the front and rear of the gate, the center of the cavity, and an end point away from the gate; The process control module is used to calculate the pressure holding index, peak pressure index, residual pressure drop index and pressure integral index based on the system pressure data and the in-mold pressure data. The pressure holding index is the average pressure of the mold in the pressure holding stage, the peak pressure index is the maximum pressure of the mold in the compression stage, the residual pressure drop index is the average drop of the mold in the cooling stage, and the pressure integral index is the integral of the pressure curve of the mold in the forming cycle over time. After the pressure holding index, the peak pressure index, the residual pressure drop index and the pressure integral index are normalized, they are input into the pre-trained MLP model to predict the forming quality of the product in the mold. When there is a deviation in the predicted product quality, the process parameters of the molding machine are adjusted until the deviation is eliminated.

[0013] The technical solution disclosed in this disclosure has the following beneficial effects: The proposed quality prediction method based on the multi-layer perceptron (MLP) neural network model can not only capture the details of the pressure changes during the forming process, but also comprehensively reflect the influence of factors such as material fluidity, filling effect, and curing process on product quality by comprehensively considering the pressure data in the mold (including holding pressure index, peak pressure index, residual pressure drop index, pressure integral index, etc.). Compared with the traditional method based on a single process parameter of the molding machine, the present invention adopts more feature data, so that the model can predict the molding quality from more dimensions, thereby significantly improving the prediction accuracy, which is then fed back to the control of process parameters to improve product quality; It can automatically monitor and optimize the production process, greatly reducing the reliance on manual operation. In traditional technology, operators need to manually adjust process parameters based on experience, while the present invention realizes intelligent management of the production process through automated models and data-driven feedback mechanisms. This not only reduces the workload of operators, but also reduces the incidence of human errors and improves the consistency and reliability of production. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 This is a flow chart of a method for controlling the forming process of a corrosion-resistant spiral blade wear-resistant block in an embodiment of this specification; Figure 2 This is an example diagram of a typical cavity pressure curve in the embodiments of this specification; Figure 3 This is a structural block diagram of a forming process control system for a corrosion-resistant spiral blade wear-resistant block in an embodiment of this specification. DETAILED DESCRIPTION

[0015] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as being limited to the examples set forth herein; on the contrary, these embodiments are provided so that the present disclosure will be more comprehensive and complete, and the concepts of the example embodiments are fully conveyed to those skilled in the art. The described features, structures, or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced while omitting one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, known technical solutions are not shown or described in detail to avoid obscuring various aspects of the present disclosure.

[0016] In addition, the accompanying drawings are only schematic illustrations of the present disclosure. The same reference numerals in the figures represent the same or similar parts, and thus their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities, which do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0017] In one embodiment, if Figure 1 As shown, this specification provides a method for controlling the forming process of a corrosion-resistant spiral blade wear block, and the execution subject of the method can be a computer, a server, a mobile phone, a tablet computer, etc. The method can specifically include steps S101~S102: In step S101, system pressure data and in-mold pressure data are acquired in real time, the system pressure data is obtained by a pressure sensor installed on an ejector of a molding machine, the in-mold pressure data is obtained by a plurality of pressure sensors installed in the mold, the in-mold pressure data and the system pressure data include a pressure curve of the mold during a molding cycle, the molding cycle includes filling, compression, holding pressure and cooling stages, and the positions of the plurality of pressure sensors in the mold include at least the gate, the front and rear of the gate, the center of the cavity, and an end point away from the gate.

[0018] Among them, Figure 2 As shown, Figure 2 This is a typical cavity pressure curve, where the filling phase starts at point A and the cavity pressure signal starts at point B. In the process, the melt initially contacts the pressure sensor, and the pressure increases steadily as the filling process progresses. The filling phase ends at point C, when the cavity is filled with melt but not compressed. Then the compression process begins, and the pressure rises rapidly to the peak at point D. Therefore, during the holding phase, the melt in the cavity is maintained at a specific pressure as additional polymer melt enters the cavity to compensate for the melt shrinkage. This process continues until the gate point (represented by point E) is sealed. Subsequently, the final cooling phase occurs and lasts until the end of the cycle. During this stage, the polymer melt gradually solidifies as the coolant circulation in the cooling channels in the mold causes heat reduction. The cooling and solidification rates determine the downward trend of the cavity pressure.

[0019] In step S102, based on the system pressure data and the in-mold pressure data, the pressure holding index, peak pressure index, residual pressure drop index, and pressure integral index are calculated, wherein the pressure holding index is the average pressure of the mold in the pressure holding stage, the peak pressure index is the maximum pressure of the mold in the compression stage, the residual pressure drop index is the average drop of the mold in the cooling stage, and the pressure integral index is the integral of the pressure curve of the mold in the forming cycle over time. After the pressure holding index, the peak pressure index, the residual pressure drop index, and the pressure integral index are normalized, they are input into the pre-trained MLP model to predict the forming quality of the product in the mold. When there is a deviation in the predicted product quality, the process parameters of the molding machine are adjusted until the deviation is eliminated.

[0020] As a supplement, the calculation method of the pressure holding index is: , and is the start and end time of the pressure holding phase, where The pressure curve of the system pressure data is continuously detected by the pressure sensor installed in the ejector. The holding pressure process involves compensating for the cavity gap caused by melt shrinkage, which is crucial to the geometric quality of the molded parts.

[0021] The pressure integral index is calculated as follows: , and is the start and end time of the forming cycle, where The pressure curve of the system pressure data is also shown. The pressure integral index is related to the overall pressure characteristics of the melt during the molding process, and the deviation can reflect the change in part quality, especially the weight change.

[0022] The peak pressure index is calculated as: , The pressure curve of the mold pressure data is obtained by all sensors installed in the mold. During the molding process, the role of pressure is to drive the melt to fill the cavity. The maximum pressure affects the amount of melt filled into the cavity, thereby determining the geometric quality of the part.

[0023] The calculation formula of the residual pressure drop index is: , and are the start and end time of the cooling phase, The pressure curve is generated by two pressure sensors installed at the center of the cavity and two pressure sensors installed at the end points far from the gate in the system pressure data. The average residual pressure drop is related to the residual stress in the melt. High average residual pressure will cause geometric deformation, and low average residual pressure may cause the molded part to be too small.

[0024] Finally, the above four indicators with different numerical levels are normalized. When these indicators are used as input data for model training, fast convergence and accuracy can be achieved.

[0025] In one embodiment, the MLP model, when trained, includes: The pressure holding index, peak pressure index, residual pressure drop index and pressure integral index calculated during the production of the product are collected and normalized to the range of 0-1 to obtain input training data; Collecting product quality classification results corresponding to the input training data as training labels; Construct a multilayer perceptron neural network model, the multilayer perceptron neural network model includes an input layer, a hidden layer, and an output layer, the input layer is used to receive the input training data, the hidden layer is used to perform weighted summation on the input training data based on a nonlinear activation function, and the number of nodes is multiple times that of the input layer, and the output layer uses a Sigmoid activation function to perform activation processing based on the properties of product quality to obtain a pre-output result; The difference between the pre-output result and the training label is calculated based on a binary cross entropy loss function, and the weights and biases of the model are updated by a gradient descent algorithm according to the calculated difference.

[0026] Based on the same idea, Figure 3As shown, the exemplary embodiment of the present disclosure also provides a forming process control system for a corrosion-resistant spiral blade wear-resistant block, the system comprising: a data acquisition module 201, for acquiring system pressure data and in-mold pressure data in real time, the system pressure data being obtained by a pressure sensor installed on an ejector of a molding machine, the in-mold pressure data being obtained by a plurality of pressure sensors installed in the mold, the in-mold pressure data and the system pressure data comprising a pressure curve of the mold during a forming cycle, the forming cycle comprising filling, compression, holding pressure and cooling stages, the positions of the plurality of pressure sensors in the mold at least comprising the gate, the front and rear of the gate, the center of the cavity, and an end point away from the gate; a process control module 202, for acquiring system pressure data and in-mold pressure data based on the system pressure data; The system pressure data and the in-mold pressure data are used to calculate the pressure holding index, peak pressure index, residual pressure drop index, and pressure integral index. The pressure holding index is the average pressure of the mold in the pressure holding stage, the peak pressure index is the maximum pressure of the mold in the compression stage, the residual pressure drop index is the average drop of the mold in the cooling stage, and the pressure integral index is the integral of the pressure curve of the mold in the forming cycle over time. After the pressure holding index, the peak pressure index, the residual pressure drop index, and the pressure integral index are normalized, they are input into the pre-trained MLP model to predict the forming quality of the product in the mold. When there is a deviation in the predicted product quality, the process parameters of the molding machine are adjusted until the deviation is eliminated.

[0027] In this embodiment, the proposed quality prediction method based on the multi-layer perceptron (MLP) neural network model can not only capture the details of the pressure change during the forming process, but also comprehensively reflect the influence of factors such as material fluidity, filling effect, and curing process on product quality by comprehensively considering the pressure data in the mold (including holding pressure index, peak pressure index, residual pressure drop index, pressure integral index, etc.). Compared with the traditional method based on a single process parameter of the molding machine, the present invention adopts more feature data so that the model can predict the molding quality from more dimensions, thereby significantly improving the prediction accuracy, and then feeding back to the control of process parameters to improve product quality; it can automatically complete the monitoring and optimization of the production process, greatly reducing the dependence on manual operation. In traditional technology, the operator needs to manually adjust the process parameters based on experience, while the present invention realizes the intelligent management of the production process through an automated model and a data-driven feedback mechanism. This not only reduces the workload of operators, but also reduces the incidence of human errors and improves the consistency and reliability of production.

[0028] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the exemplary implementation of the present disclosure.

[0029] In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to the exemplary embodiment of the present disclosure, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0030] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary technical means in the art that are not disclosed in the present disclosure. The specification and embodiments are to be considered exemplary only, and the true scope and spirit of the present disclosure are indicated by the claims.

Claims

1. A method for controlling the forming process of a corrosion-resistant spiral blade wear-resistant block, characterized in that: The method comprises: Real-time acquisition of system pressure data and in-mold pressure data, wherein the system pressure data is obtained by a pressure sensor installed on an ejector of a molding machine, and the in-mold pressure data is obtained by a plurality of pressure sensors installed in the mold, wherein the in-mold pressure data and the system pressure data include a pressure curve of the mold during a molding cycle, wherein the molding cycle includes filling, compression, pressure holding and cooling stages, and the positions of the plurality of pressure sensors in the mold include at least the gate, the front and rear of the gate, the center of the cavity, and an end point away from the gate; Based on the system pressure data and the in-mold pressure data, the pressure holding index, peak pressure index, residual pressure drop index, and pressure integral index are calculated, wherein the pressure holding index is the average pressure of the mold in the pressure holding stage, the peak pressure index is the maximum pressure of the mold in the compression stage, the residual pressure drop index is the average drop of the mold in the cooling stage, and the pressure integral index is the integral of the pressure curve of the mold in the forming cycle over time. After the pressure holding index, the peak pressure index, the residual pressure drop index, and the pressure integral index are normalized, they are input into the pre-trained MLP model to predict the forming quality of the product in the mold. When there is a deviation in the predicted product quality, the process parameters of the molding machine are adjusted until the deviation is eliminated.

2. The forming process control method of the corrosion-resistant spiral blade wear-resistant block according to claim 1 is characterized in that: The calculation method of the pressure holding index is: , and is the start and end time of the pressure holding phase, is the pressure curve of the system pressure data.

3. The forming process control method of the corrosion-resistant spiral blade wear-resistant block according to claim 1 is characterized in that: The pressure integral index is calculated as follows: , and is the start and end time of the forming cycle, is the pressure curve of the system pressure data.

4. The forming process control method of the corrosion-resistant spiral blade wear-resistant block according to claim 1 is characterized in that: The peak pressure index is calculated as: , is the pressure curve of the in-mold pressure data.

5. The forming process control method of the corrosion-resistant spiral blade wear-resistant block according to claim 1 is characterized in that: The calculation formula of the residual pressure drop index is: , and are the start and end time of the cooling phase, It is a pressure curve generated by two pressure sensors installed at the center of the cavity and two pressure sensors installed at the end points away from the gate in the system pressure data.

6. The forming process control method of the corrosion-resistant spiral blade wear-resistant block according to claim 1 is characterized in that: The MLP model, when trained, includes: The pressure holding index, peak pressure index, residual pressure drop index and pressure integral index calculated during the production of the product are collected and normalized to the range of 0-1 to obtain input training data; Collecting product quality classification results corresponding to the input training data as training labels; Construct a multilayer perceptron neural network model, the multilayer perceptron neural network model includes an input layer, a hidden layer, and an output layer, the input layer is used to receive the input training data, the hidden layer is used to perform weighted summation on the input training data based on a nonlinear activation function, and the number of nodes is multiple times that of the input layer, and the output layer uses a Sigmoid activation function to perform activation processing based on the properties of product quality to obtain a pre-output result; The difference between the pre-output result and the training label is calculated based on a binary cross entropy loss function, and the weights and biases of the model are updated by a gradient descent algorithm according to the calculated difference.

7. A forming process control system for corrosion-resistant spiral blade wear-resistant blocks, characterized in that: The system comprises: A data acquisition module, used for acquiring system pressure data and in-mold pressure data in real time, wherein the system pressure data is obtained by a pressure sensor installed on an ejector of the molding machine, and the in-mold pressure data is obtained by multiple pressure sensors installed in the mold, wherein the in-mold pressure data and the system pressure data include a pressure curve of the mold during a molding cycle, wherein the molding cycle includes filling, compression, pressure holding and cooling stages, and the positions of the multiple pressure sensors in the mold include at least the gate, the front and rear of the gate, the center of the cavity, and an end point away from the gate; The process control module is used to calculate the pressure holding index, peak pressure index, residual pressure drop index and pressure integral index based on the system pressure data and the in-mold pressure data. The pressure holding index is the average pressure of the mold in the pressure holding stage, the peak pressure index is the maximum pressure of the mold in the compression stage, the residual pressure drop index is the average drop of the mold in the cooling stage, and the pressure integral index is the integral of the pressure curve of the mold in the forming cycle over time. After the pressure holding index, the peak pressure index, the residual pressure drop index and the pressure integral index are normalized, they are input into the pre-trained MLP model to predict the forming quality of the product in the mold. When there is a deviation in the predicted product quality, the process parameters of the molding machine are adjusted until the deviation is eliminated.

Images