Carton humidity monitoring method and system

Abstract

The invention relates to a carton humidity monitoring method and system, and relates to the technical field of carton management, and the method comprises the steps: obtaining the color information of the surface of a carton based on an RGB camera; acquiring temperature distribution information of the surface of the carton based on infrared thermal imaging equipment; obtaining structure change information of the surface of the carton based on a 3D scanner; inputting the color information, the temperature distribution information and the structure change information into a multi-modal fusion network for feature level fusion to obtain carton humidity feature representation; performing decision fusion according to a temperature change algorithm and the carton humidity feature representation to obtain a carton humidity estimated value; judging whether the carton humidity estimation value is a preset value or not; and if yes, generating a corresponding control action.

Description

Technical Field

[0001] The present application relates to the technical field of carton management, and in particular to a carton humidity monitoring method and system. Background Art

[0002] With the rapid development of the logistics industry, the requirements for the protection of packaging materials are also increasing. After the cartons are produced, they are usually placed in the warehouse for storage. During the storage process, the cartons are easily affected by moisture, resulting in a decrease in strength, which is not conducive to the packaging of goods.

[0003] Therefore, how to automatically monitor the humidity of cartons and take action is a technical challenge that technicians in this field need to overcome. Summary of the invention

[0004] In order to at least partially solve the above technical problems, the present application provides a carton humidity monitoring method and system.

[0005] In a first aspect, a carton humidity monitoring method provided in the present application adopts the following technical solution.

[0006] Obtain the color information of the carton surface based on the RGB camera; Obtain the temperature distribution information on the carton surface based on infrared thermal imaging equipment; Obtain structural change information on the carton surface based on a 3D scanner; Inputting the color information, temperature distribution information and structural change information into a multimodal fusion network for feature-level fusion to obtain a feature representation of carton humidity; A decision fusion is performed based on the temperature change algorithm and the carton humidity feature representation to obtain a carton humidity estimation value; Determine whether the estimated value of the carton humidity is a preset value; if so, generate a corresponding control action.

[0007] Optionally, obtain the color information of the carton surface based on the RGB camera, including: Control adjustable light source to work for lighting; Feedback of light source brightness information through ambient light sensors; Based on the light source brightness information, the brightness of the adjustable light source is controlled by a PID algorithm to adjust until the feedback light source brightness information obtained again reaches a preset range; Acquire the carton surface image through the RGB camera; Performing image quality enhancement processing on the collected carton surface image; the image quality enhancement processing includes contrast enhancement and sharpening; The carton surface image is separated from the background by image segmentation technology; the color information of the carton surface image separated from the background is extracted to obtain the color information of the carton surface.

[0008] Optionally, based on the light source brightness information, the brightness of the adjustable light source is controlled by a PID algorithm to adjust until the retrieved feedback light source brightness information reaches a preset range, including: Obtaining the current environment brightness based on the light source brightness information; Subtract the current environment brightness from the target brightness to obtain the brightness error; Calculate the proportional term, integral term and differential term in the PID algorithm to obtain the output value; The brightness of the adjustable light source is controlled and adjusted according to the output value.

[0009] Optionally, the color information, temperature distribution information and structural change information are input into a multimodal fusion network for feature-level fusion to obtain a feature representation of carton humidity, including: Preprocessing the color information, temperature distribution information and structural change information, wherein the preprocessing includes normalization, denoising and feature point extraction; Input the preprocessed information into each branch of the multimodal fusion network; Interactive learning of cross-modal features within the network to generate richer feature representations; Perform feature-level fusion at the output layer of the network to generate a feature representation of carton humidity; Among them, interactive learning of cross-modal features is performed within the network to generate richer feature representations, including: Obtain data samples of different modalities from multiple data sources; Preliminary feature vectors were extracted using a feature extractor designed for each modality; The preliminary feature vector is input into a cross-modal fusion module, and the cross-modal fusion module realizes feature conversion and enhancement between modalities through a preset mapping relationship; In the feature interaction stage, the attention mechanism is used to dynamically select the most correlated features between different modalities for fusion, thereby generating a richer feature representation; Optimize model parameters through back-propagation algorithm; After training is complete, the generated feature representations are used to make predictions or decisions on new input data.

[0010] Optionally, a decision fusion is performed based on the temperature change algorithm and the carton humidity feature representation to obtain a carton humidity estimation value, b, including: Analyzing the carton humidity characteristic representation to obtain a preliminary humidity estimation value; Combined with the temperature distribution information, the temperature change algorithm is used to correct the initial humidity estimate; Compare the revised humidity estimates with historical data for trend analysis; Decision fusion is performed based on the trend analysis results to obtain the final estimated value of carton humidity; The trend analysis includes: Build a time series of humidity estimates; Calculate the moving average of a time series; Determine the trend of the moving average; Adjust humidity estimates based on changing trends.

[0011] Optionally, determining whether the estimated carton humidity value is a preset value; if so, generating a corresponding control action, including: Set multi-level humidity thresholds to distinguish risk levels at different humidity levels; When the estimated moisture content of a carton exceeds the first-level threshold, the carton is recorded and marked; When the estimated carton moisture exceeds the secondary threshold, a warning notification is sent to the operator and the drying equipment is started; When the estimated carton humidity exceeds the third-level threshold, the drying equipment is immediately started and an alarm message is issued.

[0012] Optionally, interactive learning of cross-modal features is performed within the network to generate richer feature representations, including: Obtain data samples of different modalities from multiple data sources; Preliminary feature vectors were extracted using a feature extractor designed for each modality; The preliminary feature vector is input into a cross-modal fusion module, and the cross-modal fusion module realizes feature conversion and enhancement between modalities through a preset mapping relationship; In the feature interaction stage, the attention mechanism is used to dynamically select the most correlated features between different modalities for fusion, thereby generating richer feature representations.

[0013] Optionally, the cross-modal fusion module specifically includes: Inputting preliminary feature vectors of different modalities into respective sub-networks for preliminary feature conversion; the sub-networks include fully connected layers and convolutional layers; The preliminary feature vectors of different modalities are converted into a unified spatial representation through mapping relationships; The converted feature vector is input into the gated recurrent unit of the cross-modal fusion module for interactive feature learning; Inside the gated recurrent unit, feature conversion and enhancement between modalities are achieved through a multi-layer neural network; Residual connections are added after each layer to alleviate the gradient vanishing problem, and feature fusion is performed after the last layer to generate a comprehensive feature representation.

[0014] Optional, attention mechanism, including: Calculate the similarity matrix between different modal features; Apply the softmax function to the similarity matrix to obtain the attention weight matrix; The features of different modalities are weighted and summed according to the attention weight matrix to obtain a comprehensive feature representation; The comprehensive feature representation is passed to the next layer for further feature enhancement.

[0015] In a second aspect, a carton humidity monitoring method provided in the present application adopts the following technical solution.

[0016] A carton humidity monitoring system, characterized by comprising: The first processing module is used to: obtain color information of the carton surface based on an RGB camera; The second processing module is used to obtain the temperature distribution information of the carton surface based on the infrared thermal imaging device; The third processing module is used to obtain structural change information on the surface of the carton based on a 3D scanner; The fourth processing module is used to: input the color information, temperature distribution information and structure change information into a multimodal fusion network for feature-level fusion to obtain a carton humidity feature representation; A fifth processing module is used to: perform decision fusion according to the temperature change algorithm and the carton humidity feature representation to obtain a carton humidity estimation value; The sixth processing module is used to: perform decision fusion according to the temperature change algorithm and the carton humidity feature representation to obtain a carton humidity estimation value. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a flow chart of a method for monitoring carton humidity in an embodiment of the present application; Figure 2 This is a system block diagram of a carton humidity monitoring system according to an embodiment of the present application; In the figure, 201 is a first processing module; 202 is a second processing module; 203 is a third processing module; 204 is a fourth processing module; 205 is a fifth processing module; and 206 is a sixth processing module. DETAILED DESCRIPTION

[0018] The following is combined with Figure 1-2 The present application is further described with specific embodiments: The present application embodiment discloses a method for monitoring carton humidity. Figure 1 As an implementation of a carton humidity monitoring method, a carton humidity monitoring method includes the following steps: Step 101: Acquire color information of the carton surface based on an RGB camera; Step 102: Acquire temperature distribution information on the surface of the carton based on an infrared thermal imaging device; Step 103: Acquire structural change information on the surface of the carton based on a 3D scanner; Step 104: input the color information, temperature distribution information and structure change information into a multimodal fusion network for feature-level fusion to obtain a carton humidity feature representation; Step 105, performing decision fusion according to the temperature change algorithm and the carton humidity feature representation to obtain a carton humidity estimation value; Step 106, determine whether the estimated value of the carton humidity is a preset value; if so, generate a corresponding control action.

[0019] Specifically, RGB cameras, infrared thermal imaging equipment and 3D scanners are used to obtain information such as the color, temperature distribution and structural changes of the carton, and the status of the carton is fully perceived from multiple angles.

[0020] The above different types of sensor data are input into a multimodal fusion network. At this stage, different data sets are processed and integrated to form a more complete and detailed description of the state of the carton, that is, the carton humidity feature representation. This process takes advantage of the complementarity between different sensors, so that information that may be missed by a single sensor can be supplemented by the data of other sensors.

[0021] The decision fusion is performed based on the temperature change algorithm combined with the previously obtained carton humidity feature representation. The calculated humidity estimate is compared with the preset standard or safety threshold. If the humidity exceeds the allowable range, the corresponding control action is triggered, such as an alarm or starting a drying device, thereby protecting the items in the carton from excessively high or low humidity.

[0022] As a specific implementation of a carton humidity monitoring method, the color information of the carton surface is obtained based on an RGB camera, including: Control adjustable light source to work for lighting; Feedback of light source brightness information through ambient light sensors; Based on the light source brightness information, the brightness of the adjustable light source is controlled by a PID algorithm to adjust until the feedback light source brightness information obtained again reaches a preset range; Acquire the carton surface image through the RGB camera; Performing image quality enhancement processing on the collected carton surface image; the image quality enhancement processing includes contrast enhancement and sharpening; The carton surface image is separated from the background by image segmentation technology; the color information of the carton surface image separated from the background is extracted to obtain the color information of the carton surface.

[0023] Specifically, an adjustable light source is used to illuminate the carton, and the light intensity is monitored in real time through an ambient light sensor to ensure consistent lighting conditions in any environment, thereby improving the quality of subsequent image processing. The light source brightness information is dynamically adjusted through the PID (proportional-integral-differential) algorithm to stabilize it within an ideal range, which can eliminate image quality fluctuations caused by changes in external light. The image of the carton surface is captured by an RGB camera, and the acquired image undergoes a series of image processing techniques, such as contrast enhancement and sharpening. Image quality enhancement can significantly improve the clarity of the image and make the color information more reliable. Image segmentation technology is used to separate the carton surface from the background, so that you can focus on the carton itself without being disturbed by the environment. Once the carton surface is successfully segmented, color information can be extracted from it.

[0024] As a specific implementation of a carton humidity monitoring method, based on the light source brightness information, the brightness of the adjustable light source is controlled by a PID algorithm to adjust until the feedback light source brightness information obtained again reaches a preset range, including: Obtaining the current environment brightness based on the light source brightness information; Subtract the current environment brightness from the target brightness to obtain the brightness error; Calculate the proportional term, integral term and differential term in the PID algorithm to obtain the output value; The brightness of the adjustable light source is controlled and adjusted according to the output value.

[0025] Specifically, the brightness information of the current environment is obtained through the ambient light sensor; the target brightness is a preset ideal brightness value, which represents the optimal lighting condition that the system hopes to achieve. By subtracting the current ambient brightness from the target brightness, a brightness error value can be obtained. This error value is the basis for subsequent PID control. The output value calculated by the PID algorithm is used to adjust the brightness of the adjustable light source so that the actual brightness is as close to the target brightness as possible. Through continuous feedback and adjustment, the system can maintain a stable light level and ensure the stability of image acquisition.

[0026] As a specific implementation of a carton humidity monitoring method, the color information, temperature distribution information and structure change information are input into a multimodal fusion network for feature-level fusion to obtain a carton humidity feature representation, including: Preprocessing the color information, temperature distribution information and structural change information, wherein the preprocessing includes normalization, denoising and feature point extraction; Input the preprocessed information into each branch of the multimodal fusion network; Interactive learning of cross-modal features within the network to generate richer feature representations; Perform feature-level fusion at the output layer of the network to generate a feature representation of carton humidity; Among them, interactive learning of cross-modal features is performed within the network to generate richer feature representations, including: Obtain data samples of different modalities from multiple data sources; Preliminary feature vectors were extracted using a feature extractor designed for each modality; The preliminary feature vector is input into a cross-modal fusion module, and the cross-modal fusion module realizes feature conversion and enhancement between modalities through a preset mapping relationship; In the feature interaction stage, the attention mechanism is used to dynamically select the most correlated features between different modalities for fusion, thereby generating a richer feature representation; Optimize model parameters through back-propagation algorithm; After training is complete, the generated feature representations are used to make predictions or decisions on new input data.

[0027] Specifically, the color information, temperature distribution information and structural change information are preprocessed, including normalization, denoising and feature point extraction. The purpose of preprocessing is to ensure the quality of the input data so that they are more suitable for subsequent feature extraction and fusion. Different types of information are sent to the network branch specially designed to process the corresponding modal data to ensure that the information of each modality can be effectively extracted and processed. In the output layer of the network, the feature information of all modalities is integrated to form the final feature representation of carton humidity. This process further enhances the expressive power of the features and the generalization ability of the model. The model parameters are continuously optimized through the back propagation algorithm until the model can achieve the expected performance on the training set. After training, the model can be used to predict or make decisions on new input data, such as judging the humidity status of the carton. By combining information from multiple modalities such as color, temperature distribution and structural changes, the system can capture the characteristics of carton humidity from more angles, improving the comprehensiveness and accuracy of monitoring. The cross-modal fusion module allows the features between different modalities to be converted and enhanced, while the attention mechanism helps the system focus on the most relevant feature combinations, thereby improving the quality of feature representation. Since the multimodal fusion network can process multiple types of input data and enhance feature representation through feature interaction learning, the model has better generalization ability when facing data in different scenarios.

[0028] As one implementation of a carton humidity monitoring method, a decision fusion is performed based on a temperature change algorithm and the carton humidity feature representation to obtain a carton humidity estimation value, including: Analyzing the carton humidity characteristic representation to obtain a preliminary humidity estimation value; Combined with the temperature distribution information, the temperature change algorithm is used to correct the initial humidity estimate; Compare the revised humidity estimates with historical data for trend analysis; Decision fusion is performed based on the trend analysis results to obtain the final estimated value of carton humidity; The trend analysis includes: Build a time series of humidity estimates; Calculate the moving average of a time series; Determine the trend of the moving average; Adjust humidity estimates based on changing trends.

[0029] Specifically, first, based on the carton humidity feature representation (such as the color information, temperature distribution information, and structural change information obtained through multimodal fusion as mentioned above), the system calculates a preliminary humidity estimate. Considering the impact of temperature change on carton humidity, the preliminary humidity estimate is corrected by the temperature change algorithm. This step uses temperature as an external variable to correct the humidity estimate, which increases the accuracy of the estimate. Comprehensively considering the preliminary humidity estimate, the estimate corrected by temperature change, and the results of trend analysis, decision fusion is performed to obtain a more accurate and reliable carton humidity estimate. By combining the preliminary estimate with the temperature change algorithm correction, the system not only relies on a single data source, but also comprehensively considers the impact of temperature on humidity, thereby improving the accuracy of humidity estimation. By comprehensively considering the preliminary humidity estimate, the corrected humidity estimate, and the results of trend analysis, the final humidity estimate not only reflects the current situation, but also considers the historical trend, which can better cope with the humidity monitoring needs in complex environments.

[0030] As one implementation of a carton humidity monitoring method, it is determined whether the carton humidity estimation value is a preset value; if so, a corresponding control action is generated, including: Set multi-level humidity thresholds to distinguish risk levels at different humidity levels; When the estimated moisture content of a carton exceeds the first-level threshold, the carton is recorded and marked; When the estimated carton moisture exceeds the secondary threshold, a warning notification is sent to the operator and the drying equipment is started; When the estimated carton humidity exceeds the third-level threshold, the drying equipment is immediately started and an alarm message is issued.

[0031] Specifically, three risk levels are defined according to different humidity levels, and each level corresponds to a humidity threshold, namely the first threshold, the second threshold and the third threshold. These thresholds are set to distinguish the potential risk level faced by cartons at different humidity levels. Exceeding the first threshold: At this time, the humidity has exceeded the normal range, but it is not yet to cause serious quality problems. The system will record and mark the carton for subsequent inspection. Exceeding the second threshold: The humidity has further increased to a level that may affect the quality of the product. The system will not only record and mark the carton, but also send a warning notification to the operator and start the drying equipment to reduce the humidity. Exceeding the third threshold: This is the most serious situation, with extremely high humidity, which may cause damage to the carton or other adverse consequences. The system will immediately start the drying equipment and issue an alarm message to remind relevant personnel to deal with it urgently. By setting multiple levels of humidity thresholds, the system can take corresponding early warning measures according to different humidity levels. This means that even slight humidity changes can be captured in time and appropriate actions can be taken according to their severity, thus preventing small problems from turning into big problems.

[0032] As one of the implementation methods of carton humidity monitoring, cross-modal feature interactive learning is performed within the network to generate richer feature representations, including: Obtain data samples of different modalities from multiple data sources; Preliminary feature vectors were extracted using a feature extractor designed for each modality; The preliminary feature vector is input into a cross-modal fusion module, and the cross-modal fusion module realizes feature conversion and enhancement between modalities through a preset mapping relationship; In the feature interaction stage, the attention mechanism is used to dynamically select the most correlated features between different modalities for fusion, thereby generating richer feature representations.

[0033] Specifically, due to the use of cross-modal feature interactive learning methods, the system can obtain information from multiple data sources and convert this information into useful feature vectors through feature extractors. By introducing a cross-modal fusion module and using the attention mechanism to dynamically select features, the model can show better adaptability and stability when facing different types of input data. Even if the data quality of a certain modality is poor or missing, the data of other modalities can still provide supplementary information to help the model make accurate judgments. In the carton humidity monitoring application, the comprehensive feature representation obtained by cross-modal feature interactive learning can more accurately reflect the actual situation. For example, by analyzing the interaction between temperature, humidity and other environmental factors, the system can more accurately evaluate the humidity state of the carton, thereby making more reasonable humidity control decisions. The application of the attention mechanism means that the system can allocate computing resources more efficiently when processing multimodal data. Focusing only on the most informative parts can reduce unnecessary computing overhead while ensuring that important information is not ignored.

[0034] As one implementation of a carton humidity monitoring method, the cross-modal fusion module specifically includes: Inputting preliminary feature vectors of different modalities into respective sub-networks for preliminary feature conversion; the sub-networks include fully connected layers and convolutional layers; The preliminary feature vectors of different modalities are converted into a unified spatial representation through mapping relationships; The converted feature vector is input into the gated recurrent unit of the cross-modal fusion module for interactive feature learning; Inside the gated recurrent unit, feature conversion and enhancement between modalities are achieved through a multi-layer neural network; Residual connections are added after each layer to alleviate the gradient vanishing problem, and feature fusion is performed after the last layer to generate a comprehensive feature representation.

[0035] As one of the implementation methods of a carton humidity monitoring method, the attention mechanism includes: Calculate the similarity matrix between different modal features; Apply the softmax function to the similarity matrix to obtain the attention weight matrix; The features of different modalities are weighted and summed according to the attention weight matrix to obtain a comprehensive feature representation; The comprehensive feature representation is passed to the next layer for further feature enhancement.

[0036] Specifically, the preliminary feature vectors of different modalities are first input into their respective sub-networks, which contain fully connected layers and convolutional layers. This allows for preliminary processing of the original feature vectors and extraction of more meaningful feature representations. Fully connected layers help capture the global relationship between features, while convolutional layers can extract local features. Through mapping relationships, feature vectors of different modalities are converted into the same feature space, so that features from different sources can be directly compared and fused, enhancing the consistency and comparability of features. The converted feature vectors are fed into a gated recurrent unit (GRU), a variant of a recurrent neural network (RNN) that is particularly suitable for processing sequence data. GRU controls the flow of information through a gating mechanism, allowing long-term dependencies to be maintained, thereby effectively learning features interactively. Adding residual connections after each layer helps alleviate the gradient vanishing problem and ensures the training effect of deep networks. After learning through multiple layers of neural networks, feature fusion is performed in the last layer to generate a comprehensive feature representation. This representation contains cross-modal information and more comprehensively reflects the state of carton humidity. By combining the cross-modal fusion module and the attention mechanism, this carton humidity monitoring method not only improves the quality of feature representation, but also enhances the overall performance of the model.

[0037] The present application also provides a carton humidity monitoring system, comprising: The first processing module 201 is used to: obtain color information of the carton surface based on an RGB camera; The second processing module 202 is used to obtain the temperature distribution information of the carton surface based on the infrared thermal imaging device; The third processing module 203 is used to obtain structural change information of the carton surface based on a 3D scanner; The fourth processing module 204 is used to: input the color information, temperature distribution information and structure change information into a multimodal fusion network for feature-level fusion to obtain a carton humidity feature representation; The fifth processing module 205 is used to: perform decision fusion according to the temperature change algorithm and the carton humidity feature representation to obtain a carton humidity estimation value; The sixth processing module 206 is used to perform decision fusion according to the temperature change algorithm and the carton humidity feature representation to obtain a carton humidity estimation value.

[0038] It should be noted that the above embodiments are only used to illustrate the present application and are not intended to limit the technical solutions described in the present application. Although the present application has been described in detail in this specification with reference to the above embodiments, a person of ordinary skill in the art should understand that a person of ordinary skill in the art can still modify or make equivalent substitutions to the present application, and all technical solutions and improvements thereof that do not depart from the spirit and scope of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for monitoring carton humidity, characterized in that: include: Obtain the color information of the carton surface based on the RGB camera; Obtain the temperature distribution information on the carton surface based on infrared thermal imaging equipment; Obtain structural change information on the carton surface based on a 3D scanner; Inputting the color information, temperature distribution information and structural change information into a multimodal fusion network for feature-level fusion to obtain a feature representation of carton humidity; A decision fusion is performed based on the temperature change algorithm and the carton humidity feature representation to obtain a carton humidity estimation value; Determine whether the estimated value of the carton humidity is a preset value; if so, generate a corresponding control action.

2. A carton humidity monitoring method according to claim 1, characterized in that: Obtain the color information of the carton surface based on the RGB camera, including: Control adjustable light source to work for lighting; Feedback of light source brightness information through ambient light sensors; Based on the light source brightness information, the brightness of the adjustable light source is controlled by a PID algorithm to adjust until the feedback light source brightness information obtained again reaches a preset range; Acquire the carton surface image through the RGB camera; Performing image quality enhancement processing on the collected carton surface image; the image quality enhancement processing includes contrast enhancement and sharpening; The carton surface image is separated from the background by image segmentation technology; the color information of the carton surface image separated from the background is extracted to obtain the color information of the carton surface.

3. A carton humidity monitoring method according to claim 2, characterized in that: Based on the light source brightness information, the brightness of the adjustable light source is controlled by a PID algorithm to adjust until the retrieved feedback light source brightness information reaches a preset range, including: Obtaining the current environment brightness based on the light source brightness information; Subtract the current environment brightness from the target brightness to obtain the brightness error; Calculate the proportional term, integral term and differential term in the PID algorithm to obtain the output value; The brightness of the adjustable light source is controlled and adjusted according to the output value.

4. A method for monitoring carton humidity according to claim 3, characterized in that: The color information, temperature distribution information and structural change information are input into a multimodal fusion network for feature-level fusion to obtain a carton humidity feature representation, including: Preprocessing the color information, temperature distribution information and structural change information, wherein the preprocessing includes normalization, denoising and feature point extraction; Input the preprocessed information into each branch of the multimodal fusion network; Interactive learning of cross-modal features within the network to generate richer feature representations; Perform feature-level fusion at the output layer of the network to generate a feature representation of carton humidity; Among them, interactive learning of cross-modal features is performed within the network to generate richer feature representations, including: Obtain data samples of different modalities from multiple data sources; Preliminary feature vectors were extracted using a feature extractor designed for each modality; The preliminary feature vector is input into a cross-modal fusion module, and the cross-modal fusion module realizes feature conversion and enhancement between modalities through a preset mapping relationship; In the feature interaction stage, the attention mechanism is used to dynamically select the most correlated features between different modalities for fusion, thereby generating a richer feature representation; Optimize model parameters through back-propagation algorithm; After training is complete, the generated feature representations are used to make predictions or decisions on new input data.

5. A method for monitoring carton humidity according to claim 4, characterized in that: According to the temperature change algorithm and the carton humidity feature representation, decision fusion is performed to obtain the carton humidity estimation value, including: Analyzing the carton humidity characteristic representation to obtain a preliminary humidity estimation value; Combined with the temperature distribution information, the temperature change algorithm is used to correct the initial humidity estimate; Compare the revised humidity estimates with historical data for trend analysis; Decision fusion is performed based on the trend analysis results to obtain the final estimated value of carton humidity; The trend analysis includes: Build a time series of humidity estimates; Calculate the moving average of a time series; Determine the trend of the moving average; Adjust humidity estimates based on changing trends.

6. A method for monitoring carton humidity according to claim 5, characterized in that: Determine whether the estimated value of the carton humidity is a preset value; if so, generate a corresponding control action, including: Set multi-level humidity thresholds to distinguish risk levels at different humidity levels; When the estimated moisture content of a carton exceeds the first-level threshold, the carton is recorded and marked; When the estimated carton moisture exceeds the secondary threshold, a warning notification is sent to the operator and the drying equipment is started; When the estimated carton humidity exceeds the third-level threshold, the drying equipment is immediately started and an alarm message is issued.

7. A method for monitoring carton humidity according to claim 6, characterized in that: Interactive learning of cross-modal features is performed within the network to generate richer feature representations, including: Obtain data samples of different modalities from multiple data sources; Preliminary feature vectors were extracted using a feature extractor designed for each modality; The preliminary feature vector is input into a cross-modal fusion module, and the cross-modal fusion module realizes feature conversion and enhancement between modalities through a preset mapping relationship; In the feature interaction stage, the attention mechanism is used to dynamically select the most correlated features between different modalities for fusion, thereby generating richer feature representations.

8. A method for monitoring carton humidity according to claim 7, characterized in that: The cross-modal fusion module specifically includes: Inputting preliminary feature vectors of different modalities into respective sub-networks for preliminary feature conversion; the sub-networks include fully connected layers and convolutional layers; The preliminary feature vectors of different modalities are converted into a unified spatial representation through mapping relationships; The converted feature vector is input into the gated recurrent unit of the cross-modal fusion module for interactive feature learning; Inside the gated recurrent unit, feature conversion and enhancement between modalities are achieved through a multi-layer neural network; Residual connections are added after each layer to alleviate the gradient vanishing problem, and feature fusion is performed after the last layer to generate a comprehensive feature representation.

9. A method for monitoring carton humidity according to claim 8, characterized in that: Attention mechanism, including: Calculate the similarity matrix between different modal features; Apply the softmax function to the similarity matrix to obtain the attention weight matrix; The features of different modalities are weighted and summed according to the attention weight matrix to obtain a comprehensive feature representation; The comprehensive feature representation is passed to the next layer for further feature enhancement.

10. A carton humidity monitoring system, characterized in that: include: The first processing module is used to: obtain color information of the carton surface based on an RGB camera; The second processing module is used to obtain the temperature distribution information of the carton surface based on the infrared thermal imaging device; The third processing module is used to obtain structural change information on the surface of the carton based on a 3D scanner; The fourth processing module is used to: input the color information, temperature distribution information and structure change information into a multimodal fusion network for feature-level fusion to obtain a carton humidity feature representation; A fifth processing module is used to: perform decision fusion according to the temperature change algorithm and the carton humidity feature representation to obtain a carton humidity estimation value; The sixth processing module is used to: perform decision fusion according to the temperature change algorithm and the carton humidity feature representation to obtain a carton humidity estimation value.

Images