Cloud manufacturing quality control and defect prediction method and system based on deep learning

Abstract

The invention relates to the technical field of cloud manufacturing, in particular to a cloud manufacturing quality control and defect prediction method and system based on deep learning. The method comprises the following steps: acquiring production field data in a manufacturing process through data acquisition equipment, and uploading the production field data to a cloud for next analysis; extracting information features of the production field data and performing feature fusion to obtain an information data feature set; constructing a joint deep learning prediction model, and training the joint deep learning prediction model by using the information data feature set; and completing cloud manufacturing quality control and defect prediction through the trained joint deep learning prediction model. The cloud manufacturing quality control and defect prediction are completed by extracting various characteristics of the production field data and training the joint deep learning prediction model, the quality problem and the defect prediction problem in the manufacturing process are solved, the production efficiency is effectively improved, the product quality is optimized, and the intelligent and automatic upgrading of the manufacturing process is promoted.

Description

Technical Field

[0001] The present invention relates to the field of cloud manufacturing technology, and in particular to a cloud manufacturing quality control and defect prediction method and system based on deep learning. Background Art

[0002] Cloud manufacturing is a production model that promotes collaborative work and resource sharing among multiple links and participants through information technology, the Internet of Things, and big data. Since the manufacturing process involved in cloud manufacturing is complex and affected by many factors, quality problems often occur. The dynamic and complex nature of the production process requires extremely high real-time requirements for quality control and defect prediction, which traditional quality control methods cannot meet.

[0003] In the manufacturing process, defects of various types and forms emerge in an endless stream. The characteristics and patterns of these defects are usually very complex, and traditional quality control methods have difficulty in effectively identifying and predicting these defects. Most existing quality control technologies are based on experience and rules, relying on manual monitoring and regular inspections, and it is difficult to fully utilize large-scale production data for intelligent decision-making. Therefore, traditional methods cannot accurately and real-timely perform quality control, nor can they provide comprehensive optimization support for the manufacturing process. Summary of the invention

[0004] In view of the shortcomings of existing methods and the needs of practical applications, in order to effectively improve production efficiency, optimize product quality, and promote the intelligent and automated upgrading of the manufacturing process, the quality problems and defect prediction problems in the manufacturing process are solved. On the one hand, the present invention provides a cloud manufacturing quality control and defect prediction method based on deep learning, comprising the following steps: Through data acquisition equipment, the production site data in the manufacturing process is obtained and uploaded to the cloud for further analysis; the information features of the production site data are extracted and feature fusion is performed to obtain an information data feature set; a joint deep learning prediction model is constructed, and the joint deep learning prediction model is trained using the information data feature set; cloud manufacturing quality control and defect prediction are completed through the trained joint deep learning prediction model. The present invention extracts multiple features of production site data, trains a joint deep learning prediction model, and then completes cloud manufacturing quality control and defect prediction, which solves the quality problems and defect prediction problems in the manufacturing process, effectively improves production efficiency, optimizes product quality, and promotes the intelligent and automated upgrade of the manufacturing process.

[0005] Optionally, the cloud manufacturing quality control and defect prediction method based on deep learning further includes standardizing the production site data; The standardized processing of the production site data satisfies the following formula: in, Indicates the value after normalization of numerical data. Represents numerical data. represents the mean, represents the standard deviation, Represents the normalized value of the standardized image. Represents the pixel value of the original image. Standardizing the production site data eliminates the influence of the numerical dimension on the prediction result, which is beneficial to improving the prediction efficiency of the present invention.

[0006] Optionally, the production site data includes numerical production site data and image production site data; The step of extracting information features of the production site data comprises the following steps: The statistical feature extraction method is used to extract the information features of the numerical production site data, and the principal component analysis method is used to reduce the dimension of the information features; the local features in the image production site data are extracted by a convolutional neural network, and high-level features are extracted layer by layer using multiple convolutional layers and pooling layers. The present invention uses different feature extraction methods for different types of production site data, which is conducive to the reasonable extraction of effective features of the data, and further helps to improve the accuracy of the present invention.

[0007] Optionally, feature fusion is performed on the information features to obtain an information data feature set that satisfies the following formula: in, Represents the information data feature set, , represents the weight coefficient, Represents the information characteristics of numerical production site data, The information features of image-based production site data are represented. The present invention sets the weights of information features according to actual conditions, thereby facilitating the identification of features of different types of production site data.

[0008] Optionally, the joint deep learning prediction model includes a defect category prediction sub-model and a defect occurrence probability prediction sub-model; The output layer activation function of the defect category prediction sub-model satisfies the following formula: in, Indicates the output result, represents the weight matrix of the fully connected layer, Represents the vectorization result of information data feature set, represents a bias term; the output layer activation function of the defect occurrence probability prediction sub-model adopts a linear activation function. The present invention constructs activation functions for defect categories and defect occurrence probabilities respectively, which is conducive to accurately identifying and predicting defect categories and defect occurrence probabilities, and further improving the prediction accuracy of the present invention.

[0009] Optionally, the using the information data feature set to train the joint deep learning prediction model comprises the following steps: Construct a defect category loss function and a defect occurrence probability loss function; and use the loss function and the information data feature set to train the joint deep learning prediction model. The present invention constructs loss functions for defect categories and defect occurrence probabilities respectively, which is conducive to accurately identifying and predicting defect categories and defect occurrence probabilities, and further improving the prediction accuracy of the present invention.

[0010] Optionally, the defect category loss function satisfies the following formula: in, represents the loss function value, represents the number of samples, Indicates The true labels of samples, Indicates The probability that a sample is a defective class.

[0011] Optionally, the defect occurrence probability loss function satisfies the following formula: in, represents the loss function value, represents the number of samples, Indicates The true value of the samples, Indicates The predicted value of a sample.

[0012] Optionally, the utilization loss function and the information data feature set to train the joint deep learning prediction model satisfies the following formula: in, represents the model parameters after iterative update, Model parameters before iterative update, represents the learning rate, Represents the gradient of the loss function. By calculating the loss, the model parameters can be quickly adjusted, which helps to improve the training speed of the model.

[0013] In the second aspect, in order to be able to efficiently execute a cloud manufacturing quality control and defect prediction method based on deep learning provided by the present invention, the present invention also provides a cloud manufacturing quality control and defect prediction system based on deep learning, including a processor, an input device, an output device and a memory, wherein the processor, the input device, the output device and the memory are interconnected, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions to execute a cloud manufacturing quality control and defect prediction method based on deep learning as described in the first aspect of the present invention. A cloud manufacturing quality control and defect prediction system based on deep learning of the present invention has a compact structure and stable performance, and can stably execute a cloud manufacturing quality control and defect prediction method based on deep learning provided by the present invention, further improving the overall applicability and practical application capabilities of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 A flow chart of a cloud manufacturing quality control and defect prediction method based on deep learning provided by an embodiment of the present invention; Figure 2 A framework diagram of a cloud manufacturing quality control and defect prediction system based on deep learning provided by an embodiment of the present invention; Figure 3 A schematic diagram of the structure of a cloud manufacturing quality control and defect prediction device based on deep learning provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0015] The specific embodiments of the present invention will be described in detail below. It should be noted that the embodiments described herein are only for illustration and are not intended to limit the present invention. In the following description, a large number of specific details are set forth in order to provide a thorough understanding of the present invention. However, it is obvious to those of ordinary skill in the art that these specific details do not need to be adopted to implement the present invention. In other examples, in order to avoid confusing the present invention, known circuits, software or methods are not specifically described.

[0016] Throughout the specification, references to "one embodiment," "an embodiment," "an example," or "an example" mean that a particular feature, structure, or characteristic described in conjunction with the embodiment or example is included in at least one embodiment of the present invention. Therefore, the phrases "in one embodiment," "in an embodiment," "an example," or "an example" appearing in various places throughout the specification do not necessarily all refer to the same embodiment or example. In addition, particular features, structures, or characteristics may be combined in one or more embodiments or examples in any suitable combination and / or subcombination. In addition, it should be understood by those of ordinary skill in the art that the figures provided herein are for illustrative purposes and that the figures are not necessarily drawn to scale.

[0017] See also Figure 1 In order to effectively improve production efficiency, optimize product quality, promote the intelligent and automated upgrading of the manufacturing process, and solve the quality problems and defect prediction problems in the manufacturing process. The present invention provides a cloud manufacturing quality control and defect prediction method based on deep learning, such as Figure 1 As shown, in one embodiment, the method includes the following steps: S1. Use data acquisition equipment to obtain production site data during the manufacturing process and upload it to the cloud for further analysis.

[0018] In an embodiment, the data acquisition equipment includes a temperature sensor, a humidity sensor, a pressure sensor and a high-definition camera. These data acquisition devices are used to collect environmental data and production data related to the manufacturing process, and are combined with other relevant data (such as text information) to form a data stream and upload it to the cloud database.

[0019] The data content of each sensor is marked as ,in , Indicates the sensor content The maximum value possible, is the corresponding sensor value.

[0020] The high-definition camera is used to collect high-quality image data. It has high sensitivity, high frame rate and accurate color reproduction capabilities, and can provide clear video stream data. Image data is marked as ,in , The maximum value marked for the image data.

[0021] The data flow during the upload process is as follows: in, Represents data flow, Indicates the function of data upload. Represents sensor data, represents image data, Represents additional text or metadata.

[0022] S2. Extract information features of the production site data and perform feature fusion to obtain an information data feature set.

[0023] In one embodiment, before extracting the information features of the production site data, the production site data is also standardized; The standardized processing of the production site data satisfies the following formula: in, Indicates the value after normalization of numerical data. Represents numerical data. represents the mean, represents the standard deviation, Represents the normalized value of the standardized image. Represents the pixel value of the original image. Through standardization, the numerical production field data obtained by the sensor can be converted into standardized data with zero mean and unit variance.

[0024] Furthermore, the production site data includes numerical production site data and image production site data; and extracting information features of the production site data includes the following steps: S21. Use a statistical feature extraction method to extract information features of the numerical production site data, and use a principal component analysis method to perform dimensionality reduction processing on the information features.

[0025] Extract key information from the standardized data for feature selection, and select features that have an important impact on defect prediction to reduce data dimensions and improve processing efficiency.

[0026] Statistical feature extraction methods, such as mean, variance, maximum value, minimum value, etc., are used to extract information features of the numerical production site data, and then the principal component analysis method is used to perform dimensionality reduction processing to obtain representative features.

[0027] S22. Extract local features from the image-based production site data through a convolutional neural network, and use multiple convolutional layers and pooling layers to extract high-level features layer by layer.

[0028] In an embodiment, the output of a convolution layer or a pooling layer may be selected as a feature, and these features are usually high-dimensional local feature representations. In some other embodiments, a convolutional neural network may be trained from annotated historical production data, and then feature extraction may be performed.

[0029] Furthermore, the data of different modalities are input into their respective fully connected layers for processing to obtain the output representation of each modality, and then the output results of all modalities are weighted summed or concatenated to obtain the final fused data for subsequent deep learning model training.

[0030] Specifically, the information features are fused to obtain an information data feature set that satisfies the following formula: in, Represents the information data feature set, , represents the weight coefficient, Represents the information characteristics of numerical production site data, Represents the information characteristics of image-based production site data.

[0031] Furthermore, after obtaining the information data feature set, it is also necessary to vectorize the information data feature set.

[0032] S3. Construct a joint deep learning prediction model, and use the information data feature set to train the joint deep learning prediction model.

[0033] In an embodiment, the joint deep learning prediction model includes a defect category prediction sub-model and a defect occurrence probability prediction sub-model.

[0034] Specifically, the defect category prediction sub-model adopts a convolutional neural network, which is suitable for learning the spatial features of image data and extracting local features through convolutional layers. It is suitable for defect pattern classification tasks; the defect occurrence probability prediction sub-model adopts a recurrent neural network or a long short-term memory network, which is suitable for processing time series data and can capture the time dependencies and sequence patterns in the data, and can obtain the trend changes of time series data.

[0035] Furthermore, the output layer activation function of the defect category prediction sub-model satisfies the following formula: in, Indicates the output result, represents the weight matrix of the fully connected layer, Represents the vectorization result of information data feature set, represents the bias term; The output layer activation function of the defect occurrence probability prediction sub-model adopts a linear activation function.

[0036] Furthermore, the using the information data feature set to train the joint deep learning prediction model comprises the following steps: S31. Construct defect category loss function and defect occurrence probability loss function.

[0037] Specifically, the defect category loss function satisfies the following formula: in, represents the loss function value, represents the number of samples, Indicates The true labels of samples, Indicates The probability that a sample is a defective class.

[0038] The defect occurrence probability loss function satisfies the following formula: in, represents the loss function value, represents the number of samples, Indicates The true value of the samples, Indicates The predicted value of a sample.

[0039] S32. Utilize the loss function and the information data feature set to train the joint deep learning prediction model.

[0040] In the embodiment, the joint deep learning prediction model is trained using the loss function and the information data feature set in step S32, satisfying the following formula: in, represents the model parameters after iterative update, Model parameters before iterative update, represents the learning rate, represents the gradient of the loss function.

[0041] Furthermore, when using the information data feature set to train the joint deep learning prediction model, it is necessary to divide the training set and the test set according to a certain ratio. After training the model with the training set, the test set is used to verify and evaluate the prediction performance of the model by calculating indicators such as accuracy, recall rate, and F1 score.

[0042] S4. Complete cloud manufacturing quality control and defect prediction through the trained joint deep learning prediction model.

[0043] In one embodiment, a trained joint deep learning prediction model is used to monitor data changes in the production process in real time, especially sensor data and camera image data, analyze and predict the data in real time, trigger a real-time alarm mechanism and provide feedback based on the prediction results to ensure that defects can be discovered in time and corresponding measures can be taken.

[0044] Specifically, one or more thresholds are set. Used to determine the severity or probability of a defect. Exceeding the preset threshold When a defect occurs, an alarm will be triggered; the alarm is issued in a variety of ways, such as SMS, email, App push notification or system internal message; the alarm content includes defect type, defect location, predicted probability and recommended control measures.

[0045] Furthermore, once the alarm is triggered, the production system will automatically execute corresponding feedback measures based on the defect type and prediction results. The feedback measures include but are not limited to adjusting production parameters, enabling backup production lines, starting equipment self-inspection programs, etc.

[0046] In the embodiment, a rule-based control algorithm or a reinforcement learning algorithm is used to automatically adjust the production parameters according to the prediction results. For example, if it is predicted that the temperature is too high to cause defects, the system automatically lowers the temperature setting value.

[0047] For multiple possible defects, the production system prioritizes them according to the severity and scope of the defects to ensure that the most critical defects are handled first; the alarm information and feedback measures are also displayed to the operator through the user interface, and the operator can take further manual intervention measures based on the suggestions; all alarms and feedback operations will be recorded in the cloud manufacturing database for subsequent data analysis and model optimization, forming a closed-loop feedback mechanism. Furthermore, the built-in knowledge base and rule engine can also generate specific repair suggestions based on the defect type and prediction results. For example, for different types of defects, the system will recommend different repair measures.

[0048] In another embodiment, the cloud database is also responsible for storing all data in the quality control and defect prediction process, including sensor data, image data, prediction results, etc. The database needs to update this data in real time to ensure the timeliness of the data, and manage the data to ensure its integrity and security. The specific steps include: Data storage: All collected data, model prediction results, alarm records and feedback measures are stored in the cloud manufacturing database.

[0049] Data update: Receive and store new production data in real time to ensure that the data in the database is up to date, and perform version control and data backup to prevent data loss and damage.

[0050] Data management: The data management module organizes, retrieves, backs up and restores stored data to ensure efficient access and security of data. Data management algorithm model: Data indexing and retrieval: Use efficient database indexing algorithms, such as B-tree or hash indexes, to improve data retrieval speed.

[0051] Data backup and recovery: Perform data backup regularly and use redundant storage technology to ensure that data can be quickly restored in the event of a failure.

[0052] Data security: Encryption algorithms (such as AES) are used to encrypt stored data to ensure data confidentiality and integrity.

[0053] Model retraining: Regularly retrain the federated deep learning prediction model using the latest production data and feedback records to improve the model's prediction accuracy and adaptability.

[0054] In an embodiment, the present invention further provides a cloud manufacturing quality control and defect prediction device based on deep learning, which can stably execute a cloud manufacturing quality control and defect prediction method based on deep learning of the present invention, including the following modules: Data acquisition module: This module integrates sensors, cameras and other equipment to collect various data in the manufacturing process in real time. Sensors collect environmental data such as temperature, humidity, and pressure. Cameras are responsible for capturing images and video data during the production process. All collected data is transmitted to the cloud database processing submodule through the data upload submodule.

[0055] Multimodal data fusion module: This module is responsible for fusing multimodal data from different data sources (such as sensor data, image data, etc.). By standardizing and normalizing the data, data from different modalities can be analyzed under a unified standard and their respective features can be extracted. Data from different modalities will be integrated in this module to provide more comprehensive and accurate data input.

[0056] Joint deep learning module: The joint deep learning module is the core of the device. It uses deep learning algorithms based on deep neural networks (such as convolutional neural networks (CNN) and recurrent neural networks (RNN)) to analyze and process multimodal data. The platform can automatically learn and identify defect patterns in the data, and perform defect prediction and quality control optimization based on historical data, supporting real-time decision-making and adjustments in the manufacturing process.

[0057] Real-time alarm module: Based on the prediction results and real-time data generated by the deep learning analysis platform, the real-time alarm module is responsible for monitoring abnormal conditions in the manufacturing process. When the system detects quality problems or defect trends, the alarm module will trigger an alarm in time to remind operators to take necessary measures. The alarm information is transmitted to relevant personnel through visual, sound or remote notification to ensure that the problem can be resolved as soon as possible.

[0058] Cloud manufacturing database module: The cloud database is used to store and manage all data related to quality control and defect prediction, including sensor data, image data, prediction results, model training data, etc. The database is also responsible for regularly updating the stored data to ensure the timeliness of the data and ensure the integrity, security and reliability of the data.

[0059] The present invention not only improves the accuracy of defect prediction, but also optimizes the quality control process through real-time early warning and automatic feedback mechanisms, thereby improving product quality and production efficiency.

[0060] See also Figure 2 In an embodiment, in order to efficiently execute a cloud manufacturing quality control and defect prediction method based on deep learning provided by the present invention, the present invention also provides a cloud manufacturing quality control and defect prediction system based on deep learning, including: an input device, an output device, a processor, and a memory, wherein the input device, the output device, the processor, and the memory are interconnected, and the memory contains program instructions, and the program instructions are used for the steps of the cloud manufacturing quality control and defect prediction method based on deep learning. The cloud manufacturing quality control and defect prediction system based on deep learning of the present invention has a compact structure and stable performance, and can stably execute a cloud manufacturing quality control and defect prediction method based on deep learning of the present invention, further improving the overall applicability and practical application ability of the present invention.

[0061] In an embodiment, the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. An input device may be used to obtain data information. An output device may be used to output the results obtained by storing program instructions contained in a computer program in a memory provided by the present invention. The memory may include a read-only memory and a random access memory, and provide instructions and data to the processor. A portion of the memory may also include a non-volatile random access memory.

[0062] In yet another alternative embodiment, see Figure 3 In order to efficiently execute the cloud manufacturing quality control and defect prediction method based on deep learning provided by the present invention, this embodiment also provides a cloud manufacturing quality control and defect prediction device based on deep learning, such as Figure 3 As shown, including: The memory 10 is used to store computer programs; the processor 20 is used to execute computer programs to implement the above-mentioned cloud manufacturing quality control and defect prediction method based on deep learning. The memory 10, the processor 20, the communication interface 31 and the communication bus 32. The memory 10, the processor 20, and the communication interface 31 all communicate with each other through the communication bus 32.

[0063] In an embodiment, the memory 10 is used to store one or more program instructions. The memory 10 may store program instructions for implementing the following functions: Through data acquisition equipment, the production site data in the manufacturing process is obtained and uploaded to the cloud for further analysis; the information features of the production site data are extracted and feature fusion is performed to obtain an information data feature set; a joint deep learning prediction model is constructed, and the joint deep learning prediction model is trained using the information data feature set; cloud manufacturing quality control and defect prediction are completed through the trained joint deep learning prediction model.

[0064] In one possible implementation, the memory 10 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, and at least one application required for a function, etc.; the data storage area may store data created during use. In addition, the memory 10 may include a read-only memory and a random access memory, and provide instructions and data to the processor. A portion of the memory may also include NVRAM. The memory stores an operating system and operating instructions, executable modules or data structures, or a subset thereof, or an extended set thereof, wherein the operating instructions may include various operating instructions for implementing various operations. The operating system may include various system programs for implementing various basic tasks and processing hardware-based tasks.

[0065] The processor 20 may be a central processing unit (CPU), an application specific integrated circuit, a digital signal processor, a field programmable gate array or other programmable logic device, and the processor 20 may be a microprocessor or any conventional processor, etc. The processor 20 may call a program stored in the memory 10. The communication interface 31 may be an interface of a communication module, and is used to connect with other devices or systems.

[0066] Of course, it should be noted that Figure 3 The structure shown does not constitute a limitation on the cloud manufacturing quality control and defect prediction device based on deep learning in this embodiment. In actual applications, the cloud manufacturing quality control and defect prediction device based on deep learning may include Figure 3 More or fewer components than shown, or combinations of certain components.

[0067] An embodiment also provides a storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the above-mentioned deep learning-based cloud manufacturing quality control and defect prediction method are implemented.

[0068] The storage medium may include: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0069] In summary, the present invention extracts multiple features of production site data, retrains a joint deep learning prediction model, and then completes cloud manufacturing quality control and defect prediction, thereby solving quality problems and defect prediction problems in the manufacturing process, effectively improving production efficiency, optimizing product quality, and promoting the intelligent and automated upgrading of the manufacturing process.

[0070] Therefore, the present invention effectively overcomes various shortcomings in the prior art and has high industrial utilization value.

[0071] 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 replace some or all of the technical features therein by equivalents. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope recorded in the present invention.

Claims

1. A cloud manufacturing quality control and defect prediction method based on deep learning, characterized in that: The following steps are involved: Through data acquisition equipment, the production site data in the manufacturing process is obtained and uploaded to the cloud for further analysis; Extracting information features of the production site data and performing feature fusion to obtain an information data feature set; Constructing a joint deep learning prediction model, and training the joint deep learning prediction model using the information data feature set; Cloud manufacturing quality control and defect prediction are completed through the trained joint deep learning prediction model.

2. The cloud manufacturing quality control and defect prediction method based on deep learning according to claim 1 is characterized in that: It also includes standardizing the production site data; The standardized processing of the production site data satisfies the following formula: in, Indicates the value after normalization of numerical data. Represents numerical data. represents the mean, represents the standard deviation, Represents the normalized value of the standardized image. Represents the pixel values ​​of the original image.

3. The cloud manufacturing quality control and defect prediction method based on deep learning according to claim 1 is characterized in that: The production site data includes numerical production site data and image production site data; The step of extracting information features of the production site data comprises the following steps: A statistical feature extraction method is used to extract information features of the numerical production field data, and a principal component analysis method is used to perform dimensionality reduction processing on the information features; The local features in the image-based production site data are extracted through a convolutional neural network, and high-level features are extracted layer by layer using multiple convolutional layers and pooling layers.

4. The cloud manufacturing quality control and defect prediction method based on deep learning according to claim 1 is characterized in that: The information features are subjected to feature fusion to obtain an information data feature set that satisfies the following formula: in, Represents the information data feature set, , represents the weight coefficient, Represents the information characteristics of numerical production site data, Represents the information characteristics of image-based production site data.

5. The cloud manufacturing quality control and defect prediction method based on deep learning according to claim 1 is characterized in that: The joint deep learning prediction model includes a defect category prediction sub-model and a defect occurrence probability prediction sub-model; The output layer activation function of the defect category prediction sub-model satisfies the following formula: in, Indicates the output result, represents the weight matrix of the fully connected layer, Represents the vectorization result of information data feature set, represents the bias term; The output layer activation function of the defect occurrence probability prediction sub-model adopts a linear activation function.

6. The cloud manufacturing quality control and defect prediction method based on deep learning according to claim 1 is characterized in that: The method of training the joint deep learning prediction model using the information data feature set comprises the following steps: Construct defect category loss function and defect occurrence probability loss function; The joint deep learning prediction model is trained using a loss function and the information data feature set.

7. The cloud manufacturing quality control and defect prediction method based on deep learning according to claim 6 is characterized in that: The defect category loss function satisfies the following formula: in, represents the loss function value, represents the number of samples, Indicates The true labels of samples, Indicates The probability that a sample is a defective class.

8. The cloud manufacturing quality control and defect prediction method based on deep learning according to claim 6 is characterized in that: The defect occurrence probability loss function satisfies the following formula: in, represents the loss function value, represents the number of samples, Indicates The true value of the samples, Indicates The predicted value of a sample.

9. The cloud manufacturing quality control and defect prediction method based on deep learning according to claim 6 is characterized in that: The loss function and the information data feature set are used to train the joint deep learning prediction model, satisfying the following formula: in, represents the model parameters after iterative update, Model parameters before iterative update, represents the learning rate, represents the gradient of the loss function.

10. A cloud manufacturing quality control and defect prediction system based on deep learning, characterized in that: The deep learning-based cloud manufacturing quality control and defect prediction system includes: an input device, an output device, a processor, and a memory. The input device, output device, processor, and memory are interconnected. The memory includes program instructions, and the program instructions are used to execute the deep learning-based cloud manufacturing quality control and defect prediction method according to any one of claims 1 to 9.

Images