Precise part subtractive machining duration prediction method and device, equipment and medium

Abstract

The embodiment of the invention provides a precision part subtractive machining duration prediction method and device, equipment and a medium, and belongs to the technical field of data processing, and the method specifically comprises the steps that 1, machining duration data corresponding to a plurality of sample parts are obtained according to historical machining data; 2, obtaining a 3D model of each sample part, converting the 3D model into a structured text, and generating text data containing part description according to the structured text; 3, vectorizing the text data to generate a numerical vector; 4, training a multi-layer perceptron neural network model by using the numerical vector and the processing time length data to obtain a processing time length prediction model; and 5, obtaining the 3D model of the target part, generating text data according to the 3D model, inputting the text data into the processing duration prediction model, and obtaining the predicted processing duration of the target part. Through the scheme disclosed by the invention, the prediction efficiency, accuracy and adaptability are improved.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of data processing technology, and in particular to a method, device, equipment and medium for predicting the time required for subtractive machining of precision parts. Background Art

[0002] At present, in modern manufacturing, accurately predicting the subtractive processing time of precision parts is crucial to optimizing production plans, controlling manufacturing costs and rationally allocating resources. However, existing processing time prediction methods have limitations when facing parts with complex geometric structures and are difficult to meet actual production needs. They are mainly reflected in the following points: 1. Difficulty in estimating time due to complex geometric structures; 2. Reliance on manual analysis and low efficiency; 3. Lack of real-time response capabilities; 4. Poor applicability and insufficient scalability; 5. The influence of 3D part model accuracy and material differences.

[0003] It can be seen that there is an urgent need for a method to predict the time of subtractive machining of precision parts with high prediction efficiency, accuracy and adaptability. Summary of the invention

[0004] In view of this, the embodiments of the present disclosure provide a method, device, equipment and medium for predicting the time for subtractive machining of precision parts, which at least partially solve the problems of poor prediction efficiency, accuracy and adaptability in the prior art.

[0005] In a first aspect, an embodiment of the present disclosure provides a method for predicting the time length of subtractive machining of precision parts, comprising:

[0006] Step 1, obtaining processing time data corresponding to multiple sample parts according to historical processing data;

[0007] Step 2, obtaining the 3D model of each sample part and converting it into structured text and generating text data containing part description accordingly;

[0008] Step 3, vectorize the text data to generate a numerical vector;

[0009] Step 4, using the numerical vector and processing time data to train a multi-layer perceptron neural network model to obtain a processing time prediction model;

[0010] Step 5, obtain the 3D model of the target part and generate text data based on it to input into the processing time prediction model to obtain the predicted processing time of the target part.

[0011] According to a specific implementation of the embodiment of the present disclosure, the 3D model is in STEP format.

[0012] According to a specific implementation manner of the embodiment of the present disclosure, the part description includes geometric features, topological information and material properties of the sample part.

[0013] According to a specific implementation of the embodiment of the present disclosure, step 3 specifically includes:

[0014] The word frequency-inverse document frequency method is used to vectorize text data and generate numerical vectors.

[0015] According to a specific implementation of the embodiment of the present disclosure, after step 3, the method further includes:

[0016] Use preset methods to reduce the dimension and select features of numerical vectors;

[0017] The numerical vector after dimensionality reduction and feature screening is standardized.

[0018] According to a specific implementation manner of an embodiment of the present disclosure, the structure of the processing time prediction model is an input layer, a hidden layer, a Dropout layer and an output layer connected in sequence.

[0019] In a second aspect, an embodiment of the present disclosure provides a device for predicting the time length of subtractive machining of precision parts, comprising:

[0020] An acquisition module, used to acquire processing time data corresponding to a plurality of sample parts according to historical processing data;

[0021] A conversion module, used for acquiring the 3D model of each sample part and converting it into structured text and generating text data containing part description accordingly;

[0022] Vectorization module, used to vectorize text data and generate numerical vectors;

[0023] A training module, used to train a multi-layer perceptron neural network model using numerical vectors and processing time data to obtain a processing time prediction model;

[0024] The prediction module is used to obtain the 3D model of the target part and generate text data based on it to input into the processing time prediction model to obtain the predicted processing time of the target part.

[0025] In a third aspect, an embodiment of the present disclosure further provides an electronic device, the electronic device comprising:

[0026] at least one processor; and,

[0027] a memory communicatively connected to the at least one processor; wherein,

[0028] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method for predicting the time for subtractive machining of precision parts in the aforementioned first aspect or any implementation of the first aspect.

[0029] In a fourth aspect, an embodiment of the present disclosure further provides a non-transitory computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable the computer to execute the method for predicting the time for subtractive machining of precision parts in the aforementioned first aspect or any implementation of the first aspect.

[0030] In the fifth aspect, the embodiments of the present disclosure also provide a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer executes the method for predicting the time for subtractive machining of precision parts in the aforementioned first aspect or any implementation of the first aspect.

[0031] The precision parts subtractive processing time prediction scheme in the disclosed embodiment includes: step 1, obtaining processing time data corresponding to multiple sample parts based on historical processing data; step 2, obtaining the 3D model of each sample part and converting it into structured text and generating text data containing part description based on it; step 3, vectorizing the text data to generate a numerical vector; step 4, training a multilayer perceptron neural network model using the numerical vector and processing time data to obtain a processing time prediction model; step 5, obtaining the 3D model of the target part and generating text data based on it to input the processing time prediction model to obtain the predicted processing time of the target part.

[0032] The beneficial effects of the embodiments of the present disclosure are as follows: through the scheme of the present disclosure, the historical processing data is deeply analyzed and feature extracted, and a model that can accurately predict the time of subtractive processing is established in combination with the geometric features of the parts. The method extracts the key geometric features of the parts, converts the 3D model into structured text data, and uses a deep learning algorithm to process the feature data, accurately predicts the processing time of complex geometric parts, and improves the prediction efficiency, accuracy and adaptability. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0034] Figure 1 A schematic diagram of a process flow of a method for predicting the time required for subtractive machining of precision parts provided in an embodiment of the present disclosure;

[0035] Figure 2 A comparison chart of a real value and a predicted value provided in an embodiment of the present disclosure;

[0036] Figure 3 A schematic diagram of converting a STEP format file of a subtractive machining model of a 3D precision part provided by an embodiment of the present disclosure into a text format;

[0037] Figure 4 A structural display diagram of a model provided in an embodiment of the present disclosure;

[0038] Figure 5 A scatter plot of visualizing real values ​​and predicted values ​​provided in an embodiment of the present disclosure;

[0039] Figure 6 A schematic diagram of the structure of a precision parts subtractive machining time prediction device provided by an embodiment of the present disclosure;

[0040] Figure 7 A schematic diagram of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0041] The embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

[0042] The following describes the embodiments of the present disclosure through specific examples, and those skilled in the art can easily understand other advantages and effects of the present disclosure from the contents disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all of the embodiments. The present disclosure can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present disclosure. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present disclosure.

[0043] It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein may be embodied in a wide variety of forms, and any specific structure and / or function described herein is merely illustrative. Based on the present disclosure, it should be understood by those skilled in the art that an aspect described herein may be implemented independently of any other aspect, and two or more of these aspects may be combined in various ways. For example, any number of aspects described herein may be used to implement the device and / or practice the method. In addition, other structures and / or functionalities other than one or more of the aspects described herein may be used to implement this device and / or practice this method.

[0044] It should also be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present disclosure. The drawings only show components related to the present disclosure rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0045] Additionally, in the following description, specific details are provided to facilitate a thorough understanding of the examples. However, it will be understood by those skilled in the art that the aspects described may be practiced without these specific details.

[0046] In modern manufacturing, accurately predicting the subtractive processing time of precision parts is crucial to optimizing production plans, controlling manufacturing costs, and rationally allocating resources. However, existing processing time prediction methods have limitations when facing parts with complex geometric structures and are difficult to meet actual production needs, mainly reflected in the following points:

[0047] 1. Difficulty in estimating processing time due to complex geometric structures: Modern precision parts are becoming increasingly complex in design, and usually contain a variety of geometric features (such as grooves, holes, chamfers, curved surfaces, etc.), which directly affect processing time. Traditional prediction methods mainly rely on logical reasoning, that is, estimation is made by analyzing the geometric parameters of the parts (such as length, width, thickness) and process parameters (such as cutting speed and feed rate). However, this logic-based reasoning makes it difficult to quantify the actual impact of complex geometric features on processing time, resulting in insufficient prediction accuracy.

[0048] 2. Reliance on manual analysis and low efficiency: Traditional processing time estimation usually relies on engineers’ experience and manual analysis, such as using standard timesheets or empirical rules to manually analyze 3D model features. This method is not only time-consuming and labor-intensive, but also difficult to effectively adapt to the modern production environment with high-frequency and large-volume demands. Especially when demand fluctuates or orders change frequently, traditional methods have slow response speeds and are difficult to meet the requirements of modern manufacturing for flexibility and real-time performance.

[0049] 3. Lack of real-time response capabilities: In a dynamic production environment, timely adjustment of production plans is crucial to reducing resource waste and improving production efficiency. Existing forecasting methods are usually unable to update the forecast results of part processing time in real time, and it is difficult to meet the needs of real-time response to production scheduling and order management in modern manufacturing systems. The lack of dynamic forecasting and adjustment capabilities leads to low efficiency in production resource utilization, affecting the competitiveness of factories under changing production demands.

[0050] 4. Poor applicability and insufficient scalability: Many traditional processing time methods are currently mainly aimed at the design of parts with simple structures. When faced with complex geometric shapes or diverse designs, it is often difficult to achieve ideal results. This means that if the part structure is very complex (such as containing multiple shapes or concave and convex features), traditional methods may find it difficult to accurately predict its processing time, resulting in production planning errors and reduced efficiency. In addition, traditional prediction methods have poor scalability when dealing with new part types or multiple production process flows. When new parts or different processing methods are introduced, traditional methods usually require readjustment of the model or manual modifications, which makes it difficult to quickly adapt to changes. This limitation is particularly prominent in modern manufacturing environments because the manufacturing industry is facing rapidly changing market demands and diverse product types.

[0051] 5. Impact of 3D part model accuracy and material differences: The accuracy requirements of the parts and the materials used largely determine the processing time. For the same geometric feature, if the material hardness, wear resistance or accuracy requirements are different, the processing technology and time will also be significantly different. Traditional methods are difficult to consider these factors at the same time, which affects the accuracy of the prediction.

[0052] In summary, modern manufacturing requires a new method to achieve high-precision prediction of the subtractive machining time of precision parts, especially for complex geometric structures and multiple material properties.

[0053] The disclosed embodiment provides a method for predicting the time required for subtractive machining of precision parts, which can be applied to the process of predicting the machining time of parts in industrial manufacturing scenarios.

[0054] See also Figure 1 , is a flow chart of a method for predicting the time required for subtractive machining of precision parts provided by an embodiment of the present disclosure. Figure 1 As shown, the method mainly comprises the following steps:

[0055] Step 1, obtaining processing time data corresponding to multiple sample parts according to historical processing data;

[0056] In traditional manufacturing processes, processing time prediction usually relies on manual experience or rule-based logic methods. Although these methods are suitable for parts with simple structures and relatively simple process flows, they are insufficient when faced with precision parts with complex geometries and multiple process flows. Parts with complex structures such as concave and convex features, curved surfaces, and special-shaped designs pose a huge challenge to traditional methods, especially in terms of production planning and resource allocation, where traditional methods show obvious limitations.

[0057] In order to improve the prediction accuracy of the processing time of complex parts, the present invention tried linear regression, ridge regression and their integrated models in the initial stage, hoping to improve the model's learning ability for complex features through integrated output. Figure 2 As shown in the experimental results (MSE of integrated model: 0.0395, RMSE: 0.1987, MAE: 0.1038, R 2 :0.4340) shows that traditional regression methods have limited performance in dealing with diverse structures and multiple process flows. They face insurmountable bottlenecks when dealing with complex, nonlinear, high-dimensional features and are difficult to meet the needs of subtractive machining time prediction for precision parts. Therefore, an innovative method based on deep learning is proposed to achieve more efficient and accurate machining time prediction.

[0058] In specific implementation, the processing time prediction method of the present invention performs special preprocessing on features in the data preparation stage to ensure that the model can automatically extract useful information from a large amount of unstructured text data.

[0059] We can first obtain the processing time data corresponding to multiple sample parts based on historical processing data. The data source of processing time mainly depends on historical production data, including automatic records of machines and equipment in the production workshop, data collected by the industrial control system, and manually input production logs. These records fully reflect the actual processing time of each part, providing reliable data support for processing time prediction.

[0060] Step 2, obtaining the 3D model of each sample part and converting it into structured text and generating text data containing part description accordingly;

[0061] Optionally, the 3D model is in STEP format.

[0062] Optionally, the part description includes geometric features, topological information and material properties of the sample part.

[0063] In specific implementation, the data set can be loaded from a CSV file. The CSV file contains text data converted from a STEP file. The entire text content is used as a column of features. The different precisions and materials of the part can also be added as features. The target variable is the processing time. The feature of each data is the text content converted from a STEP file, such as Figure 3 As shown, it contains the part's geometric description, topological information, material properties and other information as model input.

[0064] For example, converting a STEP format file to text form actually converts the binary or structured data of the STEP file into a readable text format. For example, a STEP file viewer or editor, a CAD conversion tool, or a custom script can be used to convert the STEP format file to text form, or an online conversion tool can be used to convert the STEP file to a text format or other CAD-supported format. This method automatically extracts high-dimensional features through deep learning, overcoming the limitation that traditional regression methods are difficult to handle multidimensional features. Based on the 3D model in STEP format, the present invention converts part features into text data, so that the deep learning model can comprehensively analyze the complex structural features of precision parts and make accurate predictions.

[0065] Step 3, vectorize the text data to generate a numerical vector;

[0066] Based on the above embodiment, step 3 specifically includes:

[0067] The word frequency-inverse document frequency method is used to vectorize text data and generate numerical vectors.

[0068] Furthermore, after step 3, the method further includes:

[0069] Use preset methods to reduce the dimension and select features of numerical vectors;

[0070] The numerical vector after dimensionality reduction and feature screening is standardized.

[0071] In specific implementation, since the text description of STEP files is usually long and complex, in order to ensure that the model can understand and use these features, the text data must be converted into numerical form. The steps for feature vectorization and standardization are as follows:

[0072] TF-IDF vectorization: The text data is vectorized through term frequency-inverse document frequency (TF-IDF) to generate a numerical vector representation. Specifically, TF-IDF can quantify the importance of each word in the text data (such as geometric shape, connection point type, etc.) in different part texts. In this way, the weight of common words will be reduced, and terms that are important in the description of specific parts will be given higher weights. This processing helps to retain information that is critical to the prediction of processing time and avoids the model being interfered with by irrelevant general terms. After TF-IDF vectorization, the feature vector dimension is higher, but the semantic and frequency information of the text data is retained, providing rich input information for the model.

[0073] Dimensionality reduction and feature screening: In the high-dimensional vectors generated by TF-IDF vectorization, dimensionality reduction techniques (such as principal component analysis PCA or selective feature screening) can be used to reduce feature dimensions and retain features with high information content, thereby reducing computational costs. This process can reduce unnecessary noise data while retaining important information, thereby improving the efficiency of model training and prediction.

[0074] Data standardization: To ensure the consistency of model input, the feature vectors generated by TF-IDF are standardized. Standardization is to scale the feature values ​​to a distribution with a mean of 0 and a variance of 1 to eliminate the scale differences between features. For example, features of geometric descriptions and material properties may have different numerical ranges. Through standardization, it can be ensured that each feature is learned at the same scale to avoid model bias caused by scale differences. Standardization can also accelerate the convergence of the model and improve the stability and generalization ability of the model.

[0075] Step 4, using the numerical vector and processing time data to train a multi-layer perceptron neural network model to obtain a processing time prediction model;

[0076] Furthermore, the structure of the processing time prediction model is an input layer, a hidden layer, a Dropout layer and an output layer connected in sequence.

[0077] When implementing it, Figure 4 As shown, the multi-layer perceptron (MLP) neural network model of this method contains the following hierarchical structure:

[0078] Input layer: accepts the normalized feature vector.

[0079] Hidden layer: It includes multiple fully connected layers, which reduce the number of nodes layer by layer and apply batch normalization and ReLU activation function.

[0080] Dropout layer: Add a Dropout layer after the hidden layer to prevent the risk of overfitting of the model.

[0081] Output layer: The last fully connected layer outputs the predicted processing time.

[0082] Note: In addition to the neural network model, you can also use RNN, LSTM and other prediction-related models

[0083] Model training and evaluation

[0084] Loss function: The mean square error (MSE) is used to quantify the difference between the predicted value and the true value.

[0085] Optimizer: The Adam optimizer is used to accelerate convergence. Adam has an adaptive learning rate feature, which helps to process large-scale data and complex models.

[0086] Training process: In multiple iterations (such as 3000 epochs), the model is optimized by gradually reducing the training error. In order to monitor the training progress of the model in real time, the current training loss and validation loss are recorded every 10 epochs.

[0087] Evaluation indicators: Root mean square error (RMSE), mean absolute error (MAE) and R 2 Scoring is used to evaluate the prediction effect of the model to ensure its stability and accuracy in practical applications.

[0088] Evaluation metrics: MSE: 0.0036, RMSE: 0.0598, MAE: 0.0202, R2: 0.9515

[0089] The MLP model can effectively handle complex nonlinear relationships and is particularly suitable for complex time prediction required in the subtractive processing of precision parts. Since the processing of precision parts involves high-dimensional nonlinear relationships between multiple features, the multi-layer structure of MLP can better capture these feature interactions, thereby providing more accurate time prediction.

[0090] By training on a large amount of precision parts data, the MLP model has a strong generalization ability and can effectively deal with precision parts of different types and shapes. In the manufacturing process, this feature enables the model to not only provide high-precision processing time predictions for known types of parts, but also make reasonable estimates for new types of parts.

[0091] Step 5, obtain the 3D model of the target part and generate text data based on it to input into the processing time prediction model to obtain the predicted processing time of the target part.

[0092] In specific implementation, after training the processing time prediction model, when the processing time of a part needs to be predicted, the 3D model of the target part can be obtained and text data can be generated based on it to input into the processing time prediction model to obtain the predicted processing time of the target part. Figure 5 shown.

[0093] The method for predicting the time required for subtractive machining of precision parts of the present invention is mainly used in industrial manufacturing, automated production lines, and order management systems. Engineers and production planners can use this method to predict the processing time required for a large number of precision parts, thereby optimizing the production process, reducing production costs, and improving production efficiency.

[0094] The specific application scenarios are as follows:

[0095] 1. Production Scheduling

[0096] In a high-frequency and volatile production environment, production scheduling is the key to improving business operational efficiency. By accurately predicting the processing time of parts, companies can:

[0097] Optimize resource allocation: Accurate processing time prediction can help production schedulers reasonably allocate machines, tools and human resources to avoid idle or overused resources. For example, after knowing the processing time of a specific part, schedulers can arrange the appropriate machine to perform the task to avoid congestion during peak hours.

[0098] Reduce waiting time: Waiting time in the production environment directly affects efficiency and cost. By predicting the processing time, companies can better arrange the production sequence and reduce the waiting time between processes, thereby improving overall production efficiency.

[0099] Improve production flexibility: In the face of market demand, accurate processing time forecasts enable companies to respond quickly to changes and adapt production plans to new market conditions to ensure timely delivery and customer satisfaction.

[0100] 2. Supply Chain Management

[0101] In modern manufacturing companies, supply chain management is becoming increasingly important. By accurately predicting the time required for subtractive processing of precision parts, companies can receive significant support in the following aspects:

[0102] Inventory control: By predicting the processing time, companies can better control the inventory levels of raw materials and finished products. Accurate predictions help avoid shortages or surpluses of raw materials due to uncertain processing time, thereby optimizing inventory management. For example, companies can adjust the purchase volume of raw materials based on the predicted processing time to avoid capital occupancy and increased storage costs.

[0103] Demand forecasting and coordination: Companies can combine processing time forecasts with market demand data to optimize overall supply chain coordination. By understanding production cycles in advance, companies can reduce the risk of overproduction and improve response speed while meeting customer needs.

[0104] Collaboration and communication: Accurate processing time forecasts help improve collaboration and communication between suppliers, manufacturers, and distributors in each link of the supply chain. All parties can make effective plans and coordination based on the forecast results, reducing the risks caused by information asymmetry.

[0105] 3. Smart Manufacturing

[0106] Smart manufacturing is the development trend of the future manufacturing industry. Real-time prediction of the subtractive processing time of precision parts is an important part of smart manufacturing. By combining the manufacturing execution system (MES) and the enterprise resource planning system (ERP), enterprises can achieve the following goals:

[0107] Data-driven decision-making: Real-time prediction of processing time can provide important data support for MES and ERP systems, helping decision makers make more scientific and timely decisions during the production process. For example, the system can automatically adjust the production plan based on the predicted data to ensure the efficiency and stability of the production process.

[0108] Intelligence and automation: By integrating processing time prediction, enterprises can realize the intelligence and automation of the production process. The automation system can automatically allocate resources according to the prediction results, monitor the production progress in real time, and make timely adjustments when abnormalities occur, reducing manual intervention.

[0109] Continuous optimization: The continuous feedback mechanism of the intelligent manufacturing system allows enterprises to continuously optimize the production process based on real-time data. The prediction model of processing time can be combined with real-time production data, and continuously updated and optimized through machine learning and other technologies to improve the accuracy of the prediction and ultimately achieve a more efficient production process.

[0110] The method disclosed in the present invention has significant advantages in the following aspects:

[0111] 1. Automated feature extraction and accurate prediction: Deep learning models can automatically extract geometric features, topological information, material properties, etc. related to processing time from historical production data, and use this information for model training. This automated processing is particularly important in the subtractive processing of precision parts, because the processing features of parts are complex and difficult to extract manually. It reduces the reliance on manual experience, makes the prediction more accurate, and effectively improves the applicability to a variety of parts.

[0112] 2. Complex structure recognition and processing capabilities: For subtractive processing of precision parts, deep learning models can recognize complex concave and convex structures, curved surface shapes, and specific processing features (such as drilling, milling paths, etc.), thereby more accurately predicting processing time. By converting 3D model information into structured text, the model can quantify complex geometric and topological features into numerical form for efficient processing, which is particularly critical for precision parts in subtractive processing.

[0113] 3. Efficient big data processing capabilities: In the process of precision parts processing, manufacturing companies often need to process a large amount of production data. Deep learning models can quickly process and analyze this data, respond to different processing requirements and process changes in real time, and help companies cope with the rapid changes in the market environment. It is particularly suitable for production tasks with high precision and complex process requirements, such as high-efficiency prediction of multi-process and multi-type part processing.

[0114] 4. Integrated application to achieve real-time prediction: This method can be seamlessly integrated into the manufacturing execution system (MES) and enterprise resource planning system (ERP), and improve the accuracy of production planning and the rationality of resource allocation through real-time processing time prediction. Through integration with MES and ERP systems, real-time feedback on the processing time of precision parts can be provided, which facilitates accurate production planning and resource allocation, helps reduce waiting time and optimize resource allocation.

[0115] The method for predicting the time for subtractive machining of precision parts provided in this embodiment establishes a model that can accurately predict the time for subtractive machining by conducting in-depth analysis and feature extraction of historical machining data and combining the geometric features of the parts. This method extracts the key geometric features of the parts, converts the 3D model into structured text data, and uses a deep learning algorithm to process the feature data to accurately predict the machining time for complex geometric parts, thereby improving the prediction efficiency, accuracy, and adaptability.

[0116] Corresponding to the above method embodiment, see Figure 6 The embodiment of the present disclosure also provides a precision part subtractive processing time prediction device 60, comprising:

[0117] An acquisition module 601 is used to acquire processing time data corresponding to a plurality of sample parts according to historical processing data;

[0118] A conversion module 602 is used to obtain the 3D model of each sample part and convert it into structured text and generate text data containing part description accordingly;

[0119] A vectorization module 603 is used to perform vectorization processing on text data to generate a numerical vector;

[0120] A training module 604 is used to train a multi-layer perceptron neural network model using the numerical vector and the processing time data to obtain a processing time prediction model;

[0121] The prediction module 605 is used to obtain the 3D model of the target part and generate text data based on it to input into the processing time prediction model to obtain the predicted processing time of the target part.

[0122] Figure 6 The device shown can correspondingly execute the contents of the above method embodiment. For the parts not described in detail in this embodiment, refer to the contents recorded in the above method embodiment and will not be repeated here.

[0123] See also Figure 7The embodiment of the present disclosure further provides an electronic device 70, which includes: at least one processor and a memory in communication with the at least one processor. The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method for predicting the time length of subtractive machining of precision parts in the aforementioned method embodiment.

[0124] The embodiments of the present disclosure also provide a non-transitory computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable the computer to execute the method for predicting the time length of subtractive processing of precision parts in the aforementioned method embodiment.

[0125] The embodiments of the present disclosure also provide a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer executes the method for predicting the time for subtractive machining of precision parts in the aforementioned method embodiment.

[0126] Reference below Figure 7 , which shows a schematic diagram of the structure of an electronic device 70 suitable for implementing the embodiment of the present disclosure. The electronic device in the embodiment of the present disclosure may include, but is not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle terminals (such as vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 7 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0127] like Figure 7 As shown, the electronic device 70 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage device 708 into a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the electronic device 70 are also stored. The processing device 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0128] Typically, the following devices may be connected to the I / O interface 705: input devices 706 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 707 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 708 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 709. The communication device 709 may allow the electronic device 70 to communicate with other devices wirelessly or by wire to exchange data. Although the electronic device 70 with various devices is shown in the figure, it should be understood that it is not required to implement or have all the devices shown. More or fewer devices may be implemented or have alternatively.

[0129] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device 709, or installed from a storage device 708, or installed from a ROM 702. When the computer program is executed by the processing device 701, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0130] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0131] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0132] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device can execute the relevant steps of the method embodiment.

[0133] Alternatively, the computer-readable medium carries one or more programs, and when the one or more programs are executed by the electronic device, the electronic device can perform the relevant steps of the method embodiment.

[0134] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0135] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0136] The units involved in the embodiments described in the present disclosure may be implemented by software or by hardware.

[0137] It should be understood that various parts of the present disclosure may be implemented in hardware, software, firmware, or a combination thereof.

[0138] The above is only a specific implementation of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present disclosure should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. A method for predicting the time of subtractive processing of precision parts, characterized in that: include: Step 1, obtaining processing time data corresponding to multiple sample parts according to historical processing data; Step 2, obtaining the 3D model of each sample part and converting it into structured text and generating text data containing part description accordingly; Step 3, vectorize the text data to generate a numerical vector; Step 4, using the numerical vector and processing time data to train a multi-layer perceptron neural network model to obtain a processing time prediction model; Step 5, obtain the 3D model of the target part and generate text data based on it to input into the processing time prediction model to obtain the predicted processing time of the target part.

2. The method according to claim 1, characterized in that The 3D model is in STEP format.

3. The method according to claim 1, characterized in that The part description includes geometric features, topological information and material properties of the sample part.

4. The method according to claim 1, characterized in that: The step 3 specifically includes: The word frequency-inverse document frequency method is used to vectorize text data and generate numerical vectors.

5. The method according to claim 1, characterized in that After step 3, the method further comprises: Use preset methods to reduce the dimension and select features of numerical vectors; The numerical vector after dimensionality reduction and feature screening is standardized.

6. The method according to claim 1, characterized in that The structure of the processing time prediction model is an input layer, a hidden layer, a Dropout layer and an output layer connected in sequence.

7. A device for predicting the time length of subtractive processing of precision parts, characterized in that: include: An acquisition module, used to acquire processing time data corresponding to a plurality of sample parts according to historical processing data; A conversion module, used for acquiring the 3D model of each sample part and converting it into structured text and generating text data containing part description accordingly; Vectorization module, used to vectorize text data and generate numerical vectors; A training module, used to train a multi-layer perceptron neural network model using numerical vectors and processing time data to obtain a processing time prediction model; The prediction module is used to obtain the 3D model of the target part and generate text data based on it to input into the processing time prediction model to obtain the predicted processing time of the target part.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method for predicting the time length of subtractive machining of precision parts according to any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the method for predicting the time length of subtractive machining of precision parts as claimed in any one of claims 1 to 6.

Images