Real-time monitoring system for cold storage polyurethane spraying based on temperature and humidity feedback

Abstract

The present invention relates to the field of cold storage spraying technology, and discloses a real-time monitoring system for cold storage spraying polyurethane based on temperature and humidity feedback. The system includes an environment acquisition module, a state analysis module, a parameter control module, a dynamic fusion module, a pattern matching module, and a feedback execution module. The environment acquisition module acquires temperature and humidity data and sets a monitoring interval; the state analysis module divides coating detection nodes and generates feature vectors; the parameter control module separates influencing factors, establishes control rules, and acquires process parameters; the dynamic fusion module identifies the equipment state and performs dynamic compensation, and calculates parameter differences; the pattern matching module derives the optimal curing threshold and generates a deviation sequence; the feedback execution module parses the deviation sequence and generates adjustment instructions. This system realizes real-time monitoring and precise control of the cold storage spraying polyurethane process, improves the coating quality stability and construction efficiency, is suitable for cold storage construction and maintenance scenarios, and has the advantages of strong environmental adaptability and precise parameter control.

Description

Technical Field

[0001] The present invention relates to the technical field of cold storage spraying, in particular to a real-time monitoring system for cold storage spraying polyurethane based on temperature and humidity feedback. Background Art

[0002] During the construction and maintenance of cold storage, polyurethane spraying is a key process, and the quality of its coating directly affects the cold storage's thermal insulation performance, service life, and energy consumption. Traditional cold storage spraying operations rely primarily on operator experience to adjust process parameters, lacking real-time dynamic monitoring of the spraying environment (such as temperature and humidity) and the coating curing process, leading to the following significant problems:

[0003] Temperature and humidity are core environmental factors affecting polyurethane curing. Their fluctuations can directly alter the chemical reaction rate, coating thickness uniformity, and adhesion of polyurethane. For example, low temperatures can prolong curing time, leading to wrinkles or cracks on the coating surface; high humidity can cause incomplete polyurethane foaming, forming bubbles or voids, and reducing thermal insulation performance. However, traditional processes lack precise data collection and real-time feedback mechanisms for temperature and humidity parameters, making it impossible to adjust spray parameters in response to environmental changes, resulting in poor coating quality stability.

[0004] The polyurethane curing process is a complex, dynamic physical and chemical process involving the synergistic effects of multiple parameters, including atomization pressure, spray velocity, and curing parameters (such as temperature sensitivity and moisture permeability). Traditional monitoring methods can only detect a single parameter discretely, failing to systematically extract and analyze the curing parameters at each coating inspection node. This makes it difficult to construct a complete coating feature vector, making it difficult to accurately identify the root cause of coating state deviations and lacking a scientific basis for process adjustments.

[0005] The operating status of spray equipment (such as spray intervals and atomized particle size dispersion) is closely related to coating quality. Traditional systems cannot effectively identify the dynamic relationship between equipment operating status and temperature and humidity influencing factors, making it difficult to dynamically compensate for temperature and humidity response factors in real time. This leads to increased variability in coating parameters when equipment status fluctuates, making it impossible to ensure coating consistency across different spraying stages and environmental conditions.

[0006] Furthermore, existing technologies lack in-depth analysis of coating parameter variations and a dynamic matching mechanism for optimal curing thresholds. When coating conditions deviate, scientific pattern-matching algorithms cannot be used to quickly derive the optimal curing threshold and generate precise process adjustment instructions. This results in delayed spray process adjustments, impacting both application efficiency and the refinement of coating quality control. Summary of the Invention

[0007] The purpose of the present invention is to provide a real-time monitoring system for cold storage polyurethane spraying based on temperature and humidity feedback to solve the problems raised in the above background technology.

[0008] To achieve the above objectives, the present invention provides the following technical solution: a real-time monitoring system for cold storage polyurethane spraying based on temperature and humidity feedback, the system comprising:

[0009] Environmental collection module, used to obtain temperature and humidity data of the cold storage spraying operation area and set the environmental monitoring interval corresponding to the spraying stage;

[0010] The state analysis module is used to divide multiple coating detection nodes within the environmental monitoring range, extract the characteristics of the polyurethane curing parameters of each node, and generate the coating feature vector corresponding to the node;

[0011] Parameter control module, used to separate the temperature influencing factor and humidity response factor from the coating feature vector, establish the curing control rules associated with the nodes, and obtain the spraying process parameters corresponding to the rules;

[0012] Dynamic fusion module, used to identify the equipment operating status in the spraying process parameters, dynamically compensate the temperature influencing factor and humidity response factor according to the operating status, and calculate the difference in coating parameters of each node under different compensation strategies;

[0013] A pattern matching module is used to derive the optimal curing threshold according to the difference of coating parameters, and generate a coating state deviation sequence by matching the current coating parameters with the optimal curing threshold;

[0014] The feedback execution module is used to parse the coating state deviation sequence and convert the coating state deviation sequence into spraying process adjustment instructions based on the polyurethane curing parameter difference distribution of the nodes.

[0015] Preferably, the state analysis module is implemented by: constructing a spray feature library corresponding to the coating detection node, the spray feature library containing temperature and humidity data and a coating parameter vector mapped by curing parameters;

[0016] The coating parameter vectors are matched with similar spraying stages, and the coating parameter vectors are divided into spraying cluster groups according to the matching results; the distribution center points of the curing parameters are extracted from the spraying cluster groups, and the distribution center points are set as coating detection nodes.

[0017] Preferably, the spray clustering group for dividing the coating parameter vector further includes:

[0018] According to the spray thickness and environmental parameters in the coating parameter vector, the atomization pressure, spray speed and temperature and humidity gradient are extracted, and the spray feature labels are generated based on the above parameters;

[0019] The spraying feature labels are associated with the coating parameter vectors. By calculating the spraying similarity between the feature labels, the coating parameter vectors with similarity higher than the preset spraying threshold are screened to form a spraying cluster group.

[0020] Preferably, the implementation method of generating the coating feature vector corresponding to the node includes:

[0021] For each coating detection node, according to the node's spatial position in the environmental monitoring range, the node's curing fluctuation data within the preset time window is obtained, and the node's curing fluctuation coefficient is calculated;

[0022] When the curing fluctuation coefficient exceeds the first curing threshold, the node is marked as an abnormal curing node, and its curing parameters are extracted to form a coating feature vector; when the curing fluctuation coefficient is lower than the first curing threshold, the node is marked as a stable node, and the curing parameters of the node's adjacent nodes are mean fused, and the fused data are reconstructed into a coating feature vector.

[0023] Preferably, the parameter control module is implemented as follows:

[0024] Separate temperature sensitivity, moisture permeability, and atomization uniformity from the coating feature vector and generate curing control rules for the coating detection node based on these parameters;

[0025] If the number of detection nodes covered by the current curing control rule is less than the preset coverage threshold, the coating feature vectors of the adjacent nodes are traversed, and the curing indicators not included in the control rules of the adjacent nodes are added to the current rule.

[0026] Preferably, the implementation of the dynamic fusion module includes: obtaining the periodic factor of the spraying interval and the discrete factor of the atomized particle size in the equipment operation state;

[0027] A parameter compensation network associated with periodic factors and discrete factors is constructed, and the coating parameter differences under different compensation strategies are determined according to the compensation weights of each node in the network.

[0028] Preferably, constructing the parameter compensation network further includes:

[0029] Identify the time distribution characteristics of the periodic factor. If the current time distribution characteristics completely match the preset spray timing, set the periodic factor as the initial node of the parameter compensation network.

[0030] Calculate the compensation correlation between the periodic factor and the discrete factor, and generate the intermediate nodes and terminal nodes of the parameter compensation network in descending order of correlation;

[0031] The parameters of the terminal node are reversely checked. When the correlation degree of the terminal node is lower than the preset check threshold, it is output as the final node of the parameter compensation network.

[0032] Preferably, the implementation of calculating the coating parameter difference includes:

[0033] Statistical parameters compensate for the periodic factor variance and discrete factor standard deviation of each terminal node in the network, and calculate the global range of all node parameters;

[0034] The periodic factor variance of a single terminal node is subtracted from the periodic factor variance of the adjacent nodes and divided by the global range to obtain the periodic difference coefficient; at the same time, the ratio of the discrete factor standard deviation to the global range is calculated, and the weighted sum of the two is taken as the coating parameter difference of the node.

[0035] Preferably, the implementation method of deriving the optimal curing threshold includes:

[0036] Extract the curing mode with the closest difference between the historical data and the current coating parameters, and calculate the Euclidean distance between the two in spatial distribution as the first matching reference value;

[0037] Count the difference between the current coating parameter difference and the historical curing mode in peak point density, and use the density difference value as the second matching reference value;

[0038] Based on the nonlinear combination of the first matching reference value and the second matching reference value, the optimal curing threshold in the preset curing threshold table is matched.

[0039] Preferably, the implementation of the feedback execution module includes: dividing the positive compensation interval and the negative compensation interval according to the parameter difference direction of each node in the coating state deviation sequence;

[0040] The adjustment amplitude of the parameter deviation in the positive compensation interval and the correction frequency of the parameter deviation in the negative compensation interval are extracted, and the two are superimposed and combined according to the spatial weight of the coating detection node to generate the execution parameters of the spraying process adjustment instruction.

[0041] Compared with the prior art, the present invention has the following beneficial effects:

[0042] By setting environmental monitoring intervals corresponding to the spraying phase, the environmental acquisition module accurately collects and dynamically tracks temperature and humidity data in the cold storage spraying operation area. This provides a real-time, reliable environmental parameter basis for subsequent process adjustments, significantly improving the system's sensitivity and response speed to environmental changes. The state analysis module systematically extracts the curing parameters of each coating detection node by constructing a spraying feature library, dividing spraying clusters into groups, and extracting the center points of the curing parameter distribution. The generated coating feature vector can comprehensively and accurately reflect the coating state, providing a scientific analytical basis for parameter regulation and avoiding the blindness of traditional empirical adjustments.

[0043] The parameter control module separates the temperature-influencing factor and humidity-response factor from the coating's characteristic vector, establishes node-associated curing control rules, and dynamically expands the coverage of these rules to ensure targeted and comprehensive process parameter control. This module generates personalized spraying process parameters based on the real-time environment and coating status, enabling refined control of the polyurethane curing process and effectively improving the stability of coating quality.

[0044] The dynamic fusion module identifies cyclical and discrete factors in the equipment's operating state, constructs a parameter compensation network, and calculates coating parameter variance, achieving dynamic, coordinated compensation of equipment status and temperature and humidity factors. This mechanism effectively offsets the impact of equipment status fluctuations and environmental changes on coating quality in real time, ensuring that coating parameters remain within the optimal range across different spraying phases and equipment operating conditions, significantly improving the system's adaptability and robustness.

[0045] The pattern matching module derives the optimal curing threshold based on the degree of coating parameter variation and generates a state deviation sequence by matching the current coating parameters, providing a clear adjustment target for feedback execution. This module leverages historical data and intelligent algorithms to quickly match the optimal curing threshold, avoiding the inefficiency of traditional trial-and-error methods and improving the timeliness and accuracy of process adjustments.

[0046] The feedback execution module converts coating state deviation sequences into specific spray process adjustment instructions. By dividing compensation intervals and superimposing adjustment amplitudes and correction frequencies, it enables precise fine-tuning of process parameters. This module ensures a high degree of alignment between adjustment instructions and coating state deviations, enabling rapid and effective correction of coating defects, improving application efficiency and refined coating quality control. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 This is a working principle diagram of the real-time monitoring system for cold storage polyurethane spraying based on temperature and humidity feedback according to the present invention;

[0048] Figure 2 Build a spray feature library and divide the coating detection nodes into flowcharts for the state analysis module;

[0049] Figure 3 Flowchart for clustering coating parameter vectors based on spray feature labels;

[0050] Figure 4 Flowchart for curing fluctuation coefficient analysis and eigenvector generation for coating inspection nodes. DETAILED DESCRIPTION

[0051] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0052] See also Figure 1-Figure 4 The present invention relates to a real-time monitoring system for cold storage polyurethane spraying based on temperature and humidity feedback. The system includes: an environment acquisition module, a state analysis module, a parameter control module, a dynamic fusion module, a pattern matching module, and a feedback execution module. The specific implementation steps are as follows:

[0053] First, the environmental acquisition module acquires temperature and humidity data from the cold storage spraying operation area and sets environmental monitoring intervals corresponding to the spraying phase. Next, the state analysis module divides the environmental monitoring interval into multiple coating detection nodes, extracts the polyurethane curing parameters of each node, and generates a coating feature vector corresponding to the node. The parameter control module then separates the temperature influencing factor and humidity response factor from the coating feature vector, establishes curing control rules associated with the node, and obtains the spraying process parameters corresponding to the rules. The dynamic fusion module identifies the equipment operating status within the spraying process parameters, dynamically compensates the temperature influencing factor and humidity response factor based on the operating status, and calculates the coating parameter differences for each node under different compensation strategies. The pattern matching module then derives the optimal curing threshold based on the coating parameter differences and generates a coating state deviation sequence by matching the current coating parameters with the optimal curing threshold. Finally, the feedback execution module analyzes the coating state deviation sequence and, based on the parameter difference distribution of the nodes, converts it into spraying process adjustment instructions.

[0054] The technical solution of the present invention is further described in detail below with reference to specific embodiments.

[0055] Example 1

[0056] The state analysis module of the system constructs a spray feature library corresponding to the coating detection node, which contains temperature and humidity data and coating parameter vectors mapped by curing parameters. The coating parameter vectors are matched with similar spray stages, and the coating parameter vectors are divided into spray cluster groups according to the matching results. Specifically, according to the spray thickness and environmental parameters in the coating parameter vectors, the atomization pressure, spray speed and temperature and humidity change gradients are extracted, and the spray feature labels are generated based on the above parameters. The spray feature labels are associated with the coating parameter vectors, and by calculating the spray similarity between the feature labels, the coating parameter vectors with similarity higher than the preset spray threshold are screened to form a spray cluster group. The distribution center point of the curing parameters is extracted from the spray cluster group, and the distribution center point is set as the coating detection node.

[0057] For each coating detection node, the curing fluctuation data for that node within a preset time window is acquired based on its spatial position within the environmental monitoring interval, and the node's curing fluctuation coefficient is calculated. When the curing fluctuation coefficient exceeds a first curing threshold, the node is marked as an abnormal curing node, and its curing parameters are extracted to form a coating feature vector. When the curing fluctuation coefficient falls below the first curing threshold, the node is marked as a stable node, and the curing parameters of its adjacent nodes are mean-fused. The fused data is then reconstructed into a coating feature vector.

[0058] When constructing the spray feature library, the system first preprocesses the collected temperature, humidity, and curing parameter data, removing noise and performing standardization. The processed data is then mapped into a high-dimensional feature space to form a coating parameter vector. Each coating parameter vector contains features from multiple dimensions, such as the rate of change of temperature, humidity, and coating thickness. By analyzing these features, the curing state of the polyurethane coating under different environmental conditions can be accurately determined.

[0059] During similar spray phase matching, the system compares the current coating parameter vector with the spray phases in historical data. By calculating the similarity between the vectors, the most similar spray phase is identified. For example, if the current coating parameter vector and a spray phase vector in historical data are more than 80% similar, the two are considered to be in a similar spray phase. This matching method helps the system quickly locate the current spray process phase, providing a basis for subsequent analysis and control.

[0060] When dividing spraying cluster groups, the system clusters them based on the similarity between spraying feature labels. This similarity is calculated based on parameters such as atomization pressure, spraying speed, and temperature and humidity gradients. For example, if the difference in atomization pressure between two coating parameter vectors is less than 5%, the difference in spraying speed is less than 10%, and the difference in temperature and humidity gradient is less than 15%, then their spraying feature labels are considered highly similar and can be divided into the same cluster group. This clustering method can group coating parameter vectors under similar spraying conditions into one category, facilitating subsequent analysis and processing.

[0061] To extract the center point of the curing parameter distribution, the system performs a statistical analysis of the coating parameter vectors within each spray cluster. By calculating statistical quantities such as the mean and median, the center point of the curing parameter distribution is determined. For example, for all coating parameter vectors within a cluster, the mean values ​​of temperature sensitivity, moisture permeability, and atomization uniformity are calculated and used as the center point of the distribution for that cluster. This center point represents the typical characteristics of the curing parameters within that cluster and serves as a reference standard for coating inspection nodes.

[0062] When calculating a node's curing fluctuation coefficient, the system analyzes changes in the node's curing parameters within a preset time window. The curing fluctuation coefficient reflects the stability of the curing process; a larger coefficient indicates a more unstable curing process. For example, if a node experiences significant temperature sensitivity fluctuations or frequent changes in humidity permeability over a period of time, its curing fluctuation coefficient is high. By setting a first curing threshold, abnormal curing nodes can be promptly identified so that appropriate adjustments can be made.

[0063] For abnormally cured nodes, the system extracts their curing parameters to form a coating feature vector. The coating feature vector contains key information about the node during the curing process, such as temperature sensitivity, moisture permeability, etc. This information can help the system deeply analyze the causes of abnormal curing and provide a basis for subsequent parameter adjustment. For stable nodes, the system will perform mean fusion on the curing parameters of its adjacent nodes. This fusion method can make full use of the information of adjacent nodes and improve the accuracy and reliability of the coating feature vector. For example, if the adjacent nodes of a stable node have similar characteristics in terms of temperature sensitivity and moisture permeability, then after mean fusion of these characteristics, the curing status of the node can be more accurately reflected.

[0064] The system's state analysis module accurately captures changes in the curing state during the cold storage polyurethane spraying process by building a spray feature library, dividing spray cluster groups, setting coating detection nodes, and generating coating feature vectors. This analysis method not only considers the influence of environmental factors such as temperature and humidity, but also incorporates spraying process parameters, providing a solid foundation for subsequent parameter regulation and feedback control. By promptly detecting and handling abnormal curing nodes and rationally optimizing stable nodes, the system can effectively improve the quality and efficiency of cold storage polyurethane spraying, ensuring that the coating cures as expected.

[0065] Example 2

[0066] The parameter control module works by separating temperature sensitivity, moisture permeability, and atomization uniformity from the coating feature vector and generating a curing control rule for the coating detection node based on these parameters. If the number of detection nodes covered by the current curing control rule is less than a preset coverage threshold, the coating feature vectors of adjacent nodes are traversed, and any curing indicators not included in the control rules for the adjacent nodes are added to the current rule.

[0067] When separating temperature sensitivity, moisture permeability, and atomization uniformity from the coating feature vector, the system first performs a dimensional analysis on the coating feature vector to identify characteristic dimensions related to temperature, humidity, and atomization effect. These characteristic dimensions are then reduced using methods such as principal component analysis to extract the main components that represent temperature sensitivity, moisture permeability, and atomization uniformity. For example, temperature sensitivity may be related to characteristics such as the coating surface temperature change rate and temperature distribution gradient; moisture permeability may be related to characteristics such as the humidity diffusion rate and humidity gradient change within the coating; and atomization uniformity may be related to characteristics such as the size distribution and density distribution of the sprayed particles.

[0068] Based on extracted parameters such as temperature sensitivity, moisture permeability, and atomization uniformity, the system generates curing control rules for coating inspection nodes. These rules define the parameter ranges and variation trends that each coating inspection node should meet to achieve optimal curing results under different environmental conditions. For example, for a temperature-sensitive node, the curing control rule might stipulate that the ambient temperature should be maintained at 25±2°C for the first 30 minutes after spraying to ensure proper curing of the polyurethane coating.

[0069] If the system determines that the number of detection nodes covered by the current curing control rule is less than the preset coverage threshold, the current rule may be incomplete and needs further improvement. At this point, the system traverses the coating feature vectors of adjacent nodes to check whether the control rules for the adjacent nodes contain curing indicators not covered by the current rule. If any indicators are found, the system will add them to the current rule.

[0070] For example, a node's curing control rule initially only considers temperature sensitivity and atomization uniformity. However, when traversing the coating feature vectors of adjacent nodes, it is discovered that the control rule for the adjacent node includes moisture permeability, a metric that the current rule does not. In this case, the system incorporates moisture permeability into the current rule, making it more comprehensive.

[0071] When traversing the coating feature vectors of adjacent nodes, the system determines the range of adjacent nodes based on the spatial relationship between the nodes and the correlation between process parameters. Generally speaking, nodes that are close together and have similar spray process parameters are considered adjacent nodes. The system analyzes the coating feature vectors of these adjacent nodes one by one, extracts the curing index information, and compares it with the current rules.

[0072] When a fixed indicator not included in the adjacent node's control rules is added to the current rule, the system re-evaluates the rule's coverage and accuracy. If the newly added indicator significantly improves the rule's coverage of the detected node, it indicates that the rule has been effectively improved. Conversely, if the addition of the new indicator does not significantly improve the rule's coverage, the system may further screen or adjust the indicator.

[0073] When refining curing control rules, the system also considers the interrelationships between various curing indicators. For example, temperature sensitivity and humidity permeability may have a certain coupling effect, and adjusting the temperature parameter may affect the humidity response. Therefore, the system establishes a parameter correlation model to analyze the interactions between various indicators, ensuring that newly added indicators work together with existing indicators to optimize curing control results.

[0074] By dynamically improving the curing control rules, the parameter control module can continuously expand and optimize the rules based on the actual coating feature vector, better adapting them to the curing requirements of different nodes. This not only improves the system's monitoring and control accuracy of the cold storage polyurethane spraying process, but also effectively addresses various complex situations that may arise during the spraying process, ensuring the stability and consistency of coating quality.

[0075] Example 3

[0076] The dynamic fusion module obtains the periodic factor of the spraying interval and the discrete factor of the atomized particle size in the equipment operation state. A parameter compensation network associated with the periodic factor and the discrete factor is constructed. The specific steps are as follows: identify the time distribution characteristics of the periodic factor. If the current time distribution characteristics completely match the preset spray timing, the periodic factor is set as the initial node of the parameter compensation network. Calculate the compensation correlation between the periodic factor and the discrete factor, and generate the intermediate nodes and end nodes of the parameter compensation network in descending order of correlation. Perform a reverse parameter check on the end node. When the correlation of the end node is lower than the preset verification threshold, it is output as the final node of the parameter compensation network. According to the compensation weight of each node in the network, the difference in coating parameters under different compensation strategies is determined.

[0077] To determine the periodic and discrete factors associated with the equipment's operating status, the system first collects and analyzes the spray equipment's operating data in real time. The periodic factor of the spray interval reflects the temporal regularity of the spraying operation. Statistical analysis of historical spraying data reveals a standard spray timing pattern. The discrete factor of the atomized particle size describes the uniformity of the particle size distribution during the spraying process, a factor that significantly impacts coating uniformity and quality.

[0078] When constructing the parameter compensation network, the system first identifies the temporal distribution characteristics of the periodic factor. This process requires comparing the currently collected periodic factor data with the preset standard spray timing. If the two exactly match, the spraying operation is proceeding according to the predetermined time rhythm, and the periodic factor can be used as the starting point for the parameter compensation network. For example, if the preset spray timing is to spray once every 30 seconds, and the actual collected periodic factor data shows that the spraying interval is stable at around 30 seconds, the temporal distribution characteristics are considered to match.

[0079] Next, the system calculates the compensation correlation between the periodic factor and the discrete factor. This correlation reflects the mutual relationship between the two factors in affecting coating quality. For example, changes in the periodic factor may cause fluctuations in spray pressure, which in turn affects the distribution of atomized particle size. Therefore, there is a certain correlation between the two. By calculating this correlation, it is possible to determine how the two factors should be coordinated during the parameter compensation process to achieve the optimal compensation effect.

[0080] When generating the intermediate and terminal nodes of the parameter compensation network, the system arranges them in descending order of correlation. Factor combinations with higher correlations are placed higher up in the network and have a greater impact on the final compensation results. For example, if a combination of periodic and discrete factors has a high correlation, indicating a significant impact on the coating parameters, the system will place them higher up in the network and assign them a higher compensation weight.

[0081] Reverse verification of the parameters of the end nodes is a crucial step in ensuring the accuracy of the compensation network. Starting from the end nodes, the system reversely infers the parameter values ​​of each intermediate node and the initial node to verify that the original input data can be restored. If the correlation of an end node falls below the preset verification threshold, the role of that node in the compensation process is unclear and may introduce errors, so it needs to be adjusted or eliminated.

[0082] To determine coating parameter variability, the system calculates the variance of the periodic factor and the standard deviation of the discrete factor for each terminal node in the parameter compensation network and calculates the global range of all node parameters. The periodic factor variance reflects the stability of the spray interval; a larger variance indicates a less stable spray interval. The discrete factor standard deviation reflects the uniformity of the atomized particle size; a larger standard deviation indicates a less uniform particle size distribution. The global range represents the maximum range of variation across all node parameters.

[0083] The cycle variation coefficient is calculated by subtracting the variance of the period factor of a single end node from the variance of the period factor of the adjacent nodes and dividing the difference by the global range. This coefficient measures the degree of variation in the spray period of that node from that of its adjacent nodes. Simultaneously, the ratio of the standard deviation of the discrete factor to the global range reflects the degree of dispersion in atomized particle size at that node. The weighted sum of these two indices yields the coating parameter variation for that node.

[0084] This calculation method comprehensively considers both the spray cycle and atomized particle size, providing a more comprehensive reflection of changes in coating parameters. By analyzing the differences in coating parameters under different compensation strategies, the system can select the optimal compensation strategy, thereby improving the quality and stability of polyurethane spraying in cold storage.

[0085] Example 4

[0086] The pattern matching module derives the optimal curing threshold by extracting the curing pattern from the historical data that most closely matches the current coating parameter difference and calculating the Euclidean distance between the two in spatial distribution as the first matching reference value. The difference in peak point density between the current coating parameter difference and the historical curing pattern is then calculated and used as the second matching reference value. Based on the nonlinear combination of the first and second matching reference values, the module matches the optimal curing threshold from the preset curing threshold table.

[0087] To identify the curing pattern from historical data that most closely matches the current coating parameters, the system first performs a comprehensive search of the historical database. This database contains a large amount of data on spray operations under various conditions, including various temperature and humidity environments, spray process parameters, and corresponding curing results. The system then compares the currently calculated coating parameter differences with the curing patterns in the historical data, searching for the pattern with the highest similarity.

[0088] When calculating Euclidean distances in spatial distribution, the system treats coating parameter variability and historical curing patterns as points in a high-dimensional space. Each point is composed of parameters across multiple dimensions, such as temperature sensitivity, moisture permeability, and atomization uniformity. By calculating the Euclidean distance between these points, we can quantify their spatial similarity. The smaller the Euclidean distance, the closer the two points are in space, and the more similar their corresponding coating parameter variability and curing patterns are.

[0089] When calculating peak point density differences, the system analyzes the distribution of peak points in the parameter space between the current coating parameter differences and the historical curing patterns. Peak point density reflects the concentration and intensity of parameter changes. Significant differences in peak point density between the two indicate different parameter change patterns and may require different curing thresholds.

[0090] Based on the nonlinear combination of the first and second matching reference values, the system constructs a complex matching function. This function is not a simple linear addition, but rather takes into account the interaction and influence between the two reference values. For example, when the first matching reference value is small, indicating a high degree of similarity in spatial distribution, the weight of the second matching reference value may be relatively reduced; conversely, when the first matching reference value is large, the weight of the second matching reference value may be correspondingly increased.

[0091] When matching the preset curing threshold table, the system searches for the closest threshold within the table based on the matching results after nonlinear combination. This table, developed based on extensive experimental data and experience, contains the optimal threshold ranges for different curing modes. Using a precise matching algorithm, the system finds the most appropriate curing threshold from the table for the current spraying operation.

[0092] In this way, the pattern matching module can fully utilize historical data, combined with the spatial distribution of current coating parameter differences and the peak point density characteristics, to accurately derive the optimal curing threshold. This method not only considers the spatial distribution similarity of parameters, but also pays attention to the pattern and intensity of parameter changes, making the derived threshold more consistent with actual spraying conditions.

[0093] Then, by matching the current coating parameters with the optimal curing threshold, a coating state deviation sequence is generated. The system compares each parameter of the current coating with the optimal curing threshold and calculates the deviation value for each parameter. These deviation values ​​are arranged in a specific order to form the coating state deviation sequence. This deviation sequence clearly reflects the difference between the current coating parameters and the optimal curing state, providing clear adjustment direction and basis for the feedback execution module.

[0094] This implementation of the pattern matching module, through deep mining and analysis of historical data and comprehensive consideration of multiple matching reference values, can provide precise guidance on curing thresholds for the cold storage polyurethane spray coating process. This helps ensure that the spraying process proceeds according to the expected curing requirements, improves the stability and consistency of coating quality, and thus achieves precise control of the cold storage polyurethane spray coating process.

[0095] Example 5

[0096] The feedback execution module is implemented by dividing the parameter difference direction of each node in the coating state deviation sequence into positive and negative compensation intervals. The adjustment amplitude of the parameter deviation within the positive compensation interval and the correction frequency of the parameter deviation within the negative compensation interval are extracted. These two are then combined according to the spatial weight of the coating detection node to generate the execution parameters for the spray process adjustment instructions.

[0097] When assigning positive and negative compensation intervals, the system first analyzes the direction of parameter differences at each node in the coating state deviation sequence. If a node's parameter value is above the optimal curing threshold, it is assigned to the positive compensation interval; if the parameter value is below the optimal curing threshold, it is assigned to the negative compensation interval. For example, if the coating's temperature sensitivity parameter is above the optimal curing threshold, it indicates that the node may be curing too quickly, requiring negative adjustments such as cooling. Conversely, if the temperature sensitivity parameter is below the threshold, positive adjustments such as increasing the temperature are necessary.

[0098] When extracting the adjustment range for parameter deviations within the positive compensation interval, the system calculates the difference between each node's parameter value and the optimal curing threshold. The size of this difference reflects the degree of adjustment required. For example, if a node's humidity permeability parameter is 15% higher than the optimal threshold, it indicates that a significant adjustment to humidity control at that node is required. Within the negative compensation interval, the system calculates the frequency of parameter deviations, i.e., the correction frequency. Frequent parameter deviations at a node indicate that the curing state of that node is unstable and requires more frequent corrections.

[0099] When generating execution parameters for spray process adjustment instructions, the system considers the spatial weights of coating inspection nodes. Spatial weights reflect the degree to which nodes in different locations influence overall coating quality. For example, nodes located in the corners or edges of a cold storage facility may have more complex environmental conditions and a greater impact on overall quality, so their spatial weights are higher than those in the central area.

[0100] The system combines the adjustment amplitude and correction frequency according to the spatial weight to generate the final execution parameters. The specific formula is as follows:

[0101]

[0102] in: Indicates the Execution parameters of each coating detection node; Indicates the The spatial weight of a node ranges from ,determined by the location of the node in the cold storage; Indicates the The adjustment range of each node in the positive compensation interval is calculated by the parameter deviation value; Indicates the The correction frequency of each node in the negative compensation interval is obtained by counting the number of times the parameter deviation occurs.

[0103] In this way, the system can generate personalized spray process adjustment instructions based on the specific conditions of each node. For nodes with a larger spatial weight, the adjustment amplitude has a greater impact on the execution parameters; while for nodes with a smaller spatial weight, the correction frequency has a relatively greater impact. This parameter generation method, which incorporates spatial position factors, can more specifically adjust coating state deviations at different locations, thereby improving the quality and efficiency of cold storage polyurethane spraying, ensuring that the spraying process can proceed according to the expected curing requirements, and achieving effective control and optimization of the cold storage polyurethane spraying process.

[0104] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "includes," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0105] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A real-time monitoring system for cold storage polyurethane spraying based on temperature and humidity feedback, characterized in that: include: Environmental collection module, used to obtain temperature and humidity data of the cold storage spraying operation area and set the environmental monitoring interval corresponding to the spraying stage; The state analysis module is used to divide multiple coating detection nodes within the environmental monitoring range, extract the characteristics of the polyurethane curing parameters of each node, and generate the coating feature vector corresponding to the node; Parameter control module, used to separate the temperature influencing factor and humidity response factor from the coating feature vector, establish the curing control rules associated with the nodes, and obtain the spraying process parameters corresponding to the rules; Dynamic fusion module, used to identify the equipment operating status in the spraying process parameters, dynamically compensate the temperature influencing factor and humidity response factor according to the operating status, and calculate the difference in coating parameters of each node under different compensation strategies; A pattern matching module is used to derive the optimal curing threshold according to the difference of coating parameters, and generate a coating state deviation sequence by matching the current coating parameters with the optimal curing threshold; The feedback execution module is used to parse the coating state deviation sequence and convert the coating state deviation sequence into spraying process adjustment instructions based on the polyurethane curing parameter difference distribution of the nodes.

2. A real-time monitoring system for cold storage polyurethane spraying based on temperature and humidity feedback according to claim 1, characterized in that: The implementation of the state analysis module includes: building a spray feature library corresponding to the coating detection node, the spray feature library containing temperature and humidity data and coating parameter vectors mapped by curing parameters; The coating parameter vectors are matched with similar spraying stages, and the coating parameter vectors are divided into spraying cluster groups according to the matching results; the distribution center points of the curing parameters are extracted from the spraying cluster groups, and the distribution center points are set as coating detection nodes.

3. The real-time monitoring system for cold storage polyurethane spraying based on temperature and humidity feedback according to claim 2 is characterized in that: The spray clustering groups that partition the coating parameter vector also include: According to the spray thickness and environmental parameters in the coating parameter vector, the atomization pressure, spray speed and temperature and humidity gradient are extracted, and the spray feature labels are generated based on the above parameters; The spraying feature labels are associated with the coating parameter vectors. By calculating the spraying similarity between the feature labels, the coating parameter vectors with similarity higher than the preset spraying threshold are screened to form a spraying cluster group.

4. The real-time monitoring system for cold storage polyurethane spraying based on temperature and humidity feedback according to claim 1 is characterized in that: The implementation methods of generating the coating feature vector corresponding to the node include: For each coating detection node, according to the node's spatial position in the environmental monitoring range, the node's curing fluctuation data within the preset time window is obtained, and the node's curing fluctuation coefficient is calculated; When the curing fluctuation coefficient exceeds the first curing threshold, the node is marked as an abnormal curing node, and its curing parameters are extracted to form a coating feature vector; when the curing fluctuation coefficient is lower than the first curing threshold, the node is marked as a stable node, and the curing parameters of the node's adjacent nodes are mean fused, and the fused data are reconstructed into a coating feature vector.

5. The real-time monitoring system for cold storage polyurethane spraying based on temperature and humidity feedback according to claim 1 is characterized in that: The implementation methods of the parameter control module include: Separate temperature sensitivity, moisture permeability, and atomization uniformity from the coating feature vector and generate curing control rules for the coating detection node based on these parameters; If the number of detection nodes covered by the current curing control rule is less than the preset coverage threshold, the coating feature vectors of the adjacent nodes are traversed, and the curing indicators not included in the control rules of the adjacent nodes are added to the current rule.

6. The real-time monitoring system for cold storage polyurethane spraying based on temperature and humidity feedback according to claim 1 is characterized in that: The implementation of the dynamic fusion module includes: obtaining the periodic factor of the spraying interval and the discrete factor of the atomized particle size in the equipment operation state; A parameter compensation network associated with periodic factors and discrete factors is constructed, and the coating parameter differences under different compensation strategies are determined according to the compensation weights of each node in the network.

7. The real-time monitoring system for cold storage polyurethane spraying based on temperature and humidity feedback according to claim 6 is characterized in that: Constructing a parameter compensation network also includes: Identify the time distribution characteristics of the periodic factor. If the current time distribution characteristics completely match the preset spray timing, set the periodic factor as the initial node of the parameter compensation network. Calculate the compensation correlation between the periodic factor and the discrete factor, and generate the intermediate nodes and terminal nodes of the parameter compensation network in descending order of correlation; The parameters of the terminal node are reversely checked. When the correlation degree of the terminal node is lower than the preset check threshold, it is output as the final node of the parameter compensation network.

8. The real-time monitoring system for cold storage polyurethane spraying based on temperature and humidity feedback according to claim 7 is characterized in that: The implementation methods for calculating the difference in coating parameters include: Statistical parameters compensate for the periodic factor variance and discrete factor standard deviation of each terminal node in the network, and calculate the global range of all node parameters; The periodic factor variance of a single terminal node is subtracted from the periodic factor variance of the adjacent nodes and divided by the global range to obtain the periodic difference coefficient; at the same time, the ratio of the discrete factor standard deviation to the global range is calculated, and the weighted sum of the two is taken as the coating parameter difference of the node.

9. The real-time monitoring system for cold storage polyurethane spraying based on temperature and humidity feedback according to claim 1 is characterized in that: The implementation methods for deriving the optimal curing threshold include: Extract the curing mode with the closest difference between the historical data and the current coating parameters, and calculate the Euclidean distance between the two in spatial distribution as the first matching reference value; Count the difference between the current coating parameter difference and the historical curing mode in peak point density, and use the density difference value as the second matching reference value; Based on the nonlinear combination of the first matching reference value and the second matching reference value, the optimal curing threshold in the preset curing threshold table is matched.

10. The real-time monitoring system for cold storage polyurethane spraying based on temperature and humidity feedback according to claim 1 is characterized in that: The implementation method of the feedback execution module includes: dividing the positive compensation interval and the negative compensation interval according to the parameter difference direction of each node in the coating state deviation sequence; The adjustment amplitude of the parameter deviation in the positive compensation interval and the correction frequency of the parameter deviation in the negative compensation interval are extracted, and the two are superimposed and combined according to the spatial weight of the coating detection node to generate the execution parameters of the spraying process adjustment instruction.

Images