Thermal insulation brick and manufacturing method thereof

Abstract

The invention discloses a thermal insulation brick and a manufacturing method thereof, and belongs to the field of thermal insulation bricks. The heat preservation brick comprises a brick body, the brick body is composed of two brick frames, a bearing plate is arranged on the inner sides of the brick frames, a gap exists in the inner side of the bearing plate, the two ends of the bearing plate extend to the two sides of the brick frames respectively and are fixedly connected with edge sealing plates, the edge sealing plates are parallel to the brick frames, and the edge sealing plates are fixedly connected with the brick frames. The inner sides of the edge sealing plates make contact with the surface of the bricklaying frame. The bearing plate and the edge sealing plate are designed, so that an effective heat insulation space is formed in the brick body, meanwhile, the edge sealing plate and the bricklaying frame are arranged in parallel and make contact with each other, the tightness and sealing performance of the structure are ensured, the heat bridge effect is reduced, the manufacturing process of the heat preservation bricklaying brick is relatively simple, and the manufacturing cost is low. Mass production can be realized through reasonable mold design and pouring process, and meanwhile, the multi-layer protection design is also convenient for later maintenance.

Description

Technical Field

[0001] The invention relates to the technical field of thermal insulation brickwork, in particular to thermal insulation brickwork and a manufacturing method thereof. Background Art

[0002] Thermal insulation brickwork is a building material that integrates building enclosure and thermal insulation functions. It is mainly used for thermal insulation of building enclosure structures. Thermal insulation brickwork is a building material that uses high-performance commercial concrete hollow blocks as the outer shell, and fills its cavity with lightweight thermal insulation materials such as foam commercial concrete or polystyrene foam plastics. Through the production process, the block shell and the thermal insulation material are injection-molded into one. According to different manufacturing materials and processes, thermal insulation brickwork can be divided into many types, such as self-insulating blocks, composite thermal insulation blocks, etc. Among them, self-insulating blocks refer to wall structures that do not use internal and external wall insulation technology, and their own thermal indicators can meet the requirements of the current national and local energy-saving building standards.

[0003] For example, the Chinese patent application number published by me is: 202321700548.8, and the patent name is: A thermal insulation brickwork, comprising: a main building block, a thermal insulation layer, installed on one side of the outer wall of the main building block, a protective layer, installed on one side of the outer wall of the thermal insulation layer, an installation mechanism, arranged on the thermal insulation layer, a connecting mechanism, arranged between the main building block and the protective layer, and the connecting mechanism comprising a limit block, a connecting rib and two limit strips. The thermal insulation brickwork, through the connecting ribs, sequentially penetrates the main building block, the thermal insulation layer and the protective layer, and cooperates with the two limit strips and the limit block, and can fix the connection ribs for fixed limit, thereby preventing the main building block, the thermal insulation layer and the protective layer from separating, resulting in a decrease in the thermal insulation effect. The thermal insulation brickwork, through the reinforcement mechanism, connects the main building block and the protective layer together, prevents the thermal insulation layer from separating from the main building block and the protective layer, and makes the main building block, the thermal insulation layer and the protective layer more integrated, which can effectively inhibit or avoid the falling off or damage of the thermal insulation layer.

[0004] However, the existing brickwork is mainly made of poured concrete structures. The interconnected brickwork structures will conduct temperature and cause temperature dissipation during use. At the same time, when the brickwork structures connected to the internal and external environments are exposed to different temperature environments, heat energy is transferred between the brickwork structures, resulting in the generation of a temperature gradient, which causes the indoor temperature to continue to slowly lose.

[0005] Secondly, the designed cross-sectional size of the masonry is too small, and its bearing capacity is insufficient to bear the predetermined load, resulting in insufficient strength. At the same time, the holes or grooves opened on the surface of the brickwork will weaken the cross-section of the wall and reduce its overall strength. Summary of the invention

[0006] The purpose of the present invention is to solve the problem in the prior art that brickwork that is continuously in contact with the internal and external environment will cause the indoor temperature to slowly dissipate due to the temperature gradient, and to propose thermal insulation brickwork and a manufacturing method thereof.

[0007] In order to achieve the above object, the present invention adopts the following technical solutions:

[0008] The invention discloses a thermal insulation brickwork and a manufacturing method thereof, comprising a brick body, wherein the brick body is composed of two brickwork frames, a bearing plate is arranged on the inner side of the brickwork frame, a gap exists on the inner side of the bearing plate, two ends of the bearing plate respectively extend to the two sides of the brickwork frame and are fixedly connected with edge sealing plates, the edge sealing plates are parallel to the brickwork frame, the inner side of the edge sealing plates is in contact with the surface of the brickwork frame, and the materials of the edge sealing plates and the bearing plates are both thermal insulation resin materials.

[0009] As a preferred technical solution of the present application, a reinforcing rib is fixedly connected to the outer side of the bearing plate, and the reinforcing rib extends to the inside of the brick frame away from the side of the bearing plate. The inner side of the reinforcing rib is fixedly connected to an attachment rod located inside the brick frame, and the brick frame is wrapped around the surface of the reinforcing rib and the attachment rod by pouring and solidifying.

[0010] As a preferred technical solution of the present application, a support frame is fixedly connected to the outer side of the load-bearing plate, and the side of the support frame away from the load-bearing plate is in contact with the inner side of the brickwork frame, and the material of the support frame is resin material.

[0011] As a preferred technical solution of the present application, a connection frame is provided on the inner side of the load-bearing plate, and the interior of the connection frame is filled with heat-insulating material.

[0012] As a preferred technical solution of the present application, the thermal insulation material includes a nano coil filled inside a connection frame, and thermal insulation cotton boards located inside the connection frame are arranged on both sides of the nano coil.

[0013] As a preferred technical solution of the present application, connecting rods are provided at the four corners inside the connecting frame, the nano coil is wrapped on the surface of the connecting rods, both ends of the connecting rods successively penetrate the insulation cotton board, the connecting frame, the load-bearing plate and the support frame and extend to the interior of the support frame, and both ends of the connecting rods are threadedly connected with nuts located inside the support frame.

[0014] As a preferred technical solution of the present application, an insulating layer is provided on the outside of the brickwork frame, and a protective layer is provided on the outside of the insulating layer. The insulating layer includes a waterproof coating coated on the outside of the brickwork frame, and an outer layer board is adhered to the surface of the waterproof coating. The protective layer includes a plastic film fixedly connected to the surface of the outer layer board, and the surface of the plastic film is coated with a sunscreen coating.

[0015] Thermal insulation brickwork and a method for manufacturing the same comprise the following steps:

[0016] S1: According to the design size of the thermal insulation brickwork, prepare the corresponding molds, including the molds of the brickwork frame and the molds of the bearing plate, edge plate and other components. Use thermal insulation resin materials to injection mold the bearing plate and edge plate as well as the reinforcing ribs and attachment rods on both sides in the mold, and ensure that there is enough space inside the bearing plate for subsequent filling of thermal insulation materials;

[0017] S2: After the bearing plate and the edge plate are formed, necessary trimming and inspection are carried out to ensure that the size and shape meet the design requirements. When the bearing plate is processed, the support frame is fixedly connected to the outer side of the bearing plate and the bearing plate and the edge plate are moved to the inside of the bricklaying frame mold. It is ensured that the edge plate and the bricklaying frame mold are parallel to each other and the inner side is in close contact with the mold surface. The casting material of the bricklaying frame (such as concrete or other suitable materials) is poured into the mold so that the casting material completely fills the gap between the support frame and the mold. At the same time, the material fully wraps the reinforcing ribs and the attachment rods, and waits for the casting material to solidify and form a bricklaying frame;

[0018] S3: Install a connection frame on the inner side of the support plate, and fill the connection frame with nano coils and thermal insulation cotton boards. Use connecting rods to penetrate the thermal insulation cotton boards, the connection frame, the support plate and the support frame, and install nuts inside the support frame to fix the connecting rods and the thermal insulation materials.

[0019] S4: Apply a waterproof coating on the outside of the brickwork frame to form an insulating layer. After the waterproof coating is dry, adhere the outer plate to the surface of the waterproof coating and attach the plastic film to the surface of the outer plate. At the same time, apply a sunscreen coating on the surface of the plastic film to form a protective layer, thereby completing the production of thermal insulation blocks.

[0020] As a preferred technical solution of the present application, in step S3 of the thermal insulation brickwork and the method for manufacturing the same, in order to ensure the accurate filling and fixation of the thermal insulation material, it is proposed to adopt an intelligent assembly algorithm; the specific implementation process is as follows:

[0021] 1. Data Collection and Preprocessing

[0022] 1. Sensor placement

[0023] Visual sensor: High-resolution industrial cameras are placed at key locations on the assembly line to capture real-time images of insulation materials during assembly; the collected image data is represented as variable I k , where k represents the sequence number of the acquired image;

[0024] Force sensor: Force sensors are arranged at the contact parts such as connecting rods, nano coils, and thermal insulation cotton boards to monitor the force conditions of each component during the assembly process; the data of the force sensor is expressed as a variable F i , where i represents the number of the force sensor;

[0025] Temperature sensor: Arrange temperature sensors in the assembly environment to monitor the impact of ambient temperature on the filling and fixing of insulation materials; temperature data is represented by variable T j , where j represents the number of the temperature sensor;

[0026] 2. Data collection and annotation

[0027] Image data acquisition: The image data of the insulation material assembly process is collected in real time through visual sensors. The image data acquisition frequency is f I , the collected data set is represented as Where N I is the total number of image data;

[0028] Force and temperature data acquisition: Synchronously collect data from force sensors and temperature sensors. The force sensor data set is represented as The temperature sensor dataset is represented as Where N F and N T are the total number of force and temperature data, respectively;

[0029] Data annotation: Annotate the collected images and sensor data, including the specific location of the components. k , Size S k , filling density D k , stress state F i and temperature state T j ;

[0030] 3. Data Preprocessing

[0031] Image preprocessing: collect image data k After processing, the image data is represented by image enhancement, size scaling, and noise filtering.

[0032] Data normalization: force data F i and temperature data T j Normalization is performed to eliminate dimension differences; the normalization formula is as follows:

[0033] Normalize the image data:

[0034]

[0035] Among them, I k (x,y) is the original image I k The pixel value at position (x, y), I min and I max are the minimum and maximum values ​​of the image pixels, respectively. is the pixel value of the normalized image data at position (x, y);

[0036] Normalize the force sensor data:

[0037]

[0038] in, is the value of the normalized force sensor data, F i is the measured value of the original force sensor at a certain moment, F min is the minimum value of the force sensor data, F max is the maximum value of the force sensor data;

[0039] Normalize the temperature sensor data:

[0040]

[0041] in, is the value of the normalized temperature sensor data, T j is the measurement value of the original temperature sensor at a certain moment, T min is the minimum value of the temperature sensor data, T max is the maximum value of the temperature sensor data;

[0042] 2. Automatically Design Deep Learning Models Using NAS

[0043] 1. Search space definition

[0044] Convolutional layer configuration: defines the parameters of the convolutional layer, including the convolution kernel size, stride, padding method, and number of convolutional layers;

[0045] The output formula of the convolutional layer is:

[0046]

[0047] Among them, K c is the convolution kernel size, S c is the stride length, P c is the filling method, N c is the number of convolutional layers, W l is the weight matrix of the convolution kernel, b l is the bias term, O c,l is the output representation of each convolutional layer, l is the index of the convolutional layer, and m and n are variables used to index the elements inside the convolution kernel or pooling window;

[0048] Pooling layer configuration: defines the parameters of the pooling layer, including the pooling window size K p , stride S p And the number of pooling layers N p ; The output of the pooling layer is represented as Op,m ;

[0049] The output formula of the maximum pooling layer is:

[0050]

[0051] Among them, O p,m (x, y) This is the output value corresponding to the position (x, y) in the pooling layer m, max means taking the maximum value, i and j are the indexes inside the pooling window, and Kp is the size of the pooling window;

[0052] Fully connected layer configuration: defines the parameters of the fully connected layer, including the number of nodes N fc , activation function σ fc , and the number of fully connected layers L fc ; The output of the fully connected layer is represented as O fc,n , where n is the index of the fully connected layer;

[0053] The output formula of the fully connected layer is:

[0054]

[0055] Among them, O fc,n represents the value of the nth output node in the fully connected layer, σ fc is the activation function used by the fully connected layer, ∑ p represents the weighted sum of all inputs, O p,m (p) represents the value of the mth output node at index p in the previous layer, W fc,n is the weight matrix of the fully connected layer, b fc,n is the bias term;

[0056] 2. Search algorithm selection

[0057] NAS based on reinforcement learning: In this step, the NAS algorithm based on reinforcement learning is used; the parameters of the policy network are θ, the parameters of the agent network are φ, and the action sequence used is a t , the state is s t , then the policy network updates the parameters by maximizing the following objectives:

[0058] Reinforcement learning strategy update formula:

[0059]

[0060] Among them, θ t+1 is the updated policy parameter, θ t is the strategy parameter at the current moment, is the policy gradient, α is the learning rate, R t is the return value, π θis a policy controlled by parameter θ;

[0061] Evolutionary Algorithm NAS: In the evolutionary algorithm, each individual in the population represents a model architecture; the fitness function f(x) of the population contains a trade-off between accuracy and complexity, and the fitness function is defined as:

[0062] Fitness function formula:

[0063] f(x)=Accuracy(x)-λ·Complexity(x)

[0064] Among them, f(x) is the value of the fitness function, λ is the trade-off coefficient, Accuracy(x) represents the accuracy of the model, and Complexity(x) is the complexity of the model;

[0065] 3. Search process

[0066] Training model: During the search process, use the collected data set Train each model architecture generated by NAS and output the predicted insulation material positioning results

[0067] Evaluate the model: Use the validation dataset to calculate the accuracy of each architecture Accuracy(x) and select the best model architecture x based on the fitness function * ;

[0068] Model selection: Finally, the model architecture x with the largest fitness function value f(x) is selected * As the final architecture, and ready for further optimization;

[0069] 3. Combining Bayesian Optimization to Accelerate Architecture Search

[0070] 1. Introduction of Bayesian Optimization

[0071] Surrogate model selection: Use Gaussian process (GP) as the surrogate model for Bayesian optimization. The kernel function of the surrogate model is represented by k(x, x') to model the performance distribution of the NAS search space.

[0072] Gaussian process kernel function formula:

[0073]

[0074] Among them, k(x,x') is the kernel function in the Gaussian process, is the kernel function amplitude, l is the kernel function scale, x and x' are different architecture parameters, exp is the exponential function;

[0075] 2. Optimization process

[0076] Sampling and Inference: Use GP to infer the distribution of the current optimal architecture parameters and use the expected improvement (EI) strategy to select the next set of architecture parameters x to be evaluated. next ;

[0077] Expected Improvement (EI) Strategy Formula:

[0078]

[0079] Where μ(x) is the predicted mean of the GP model, σ(x) is the predicted variance, τ is the current best value, Φ and φ are the cumulative distribution function and probability density function of the standard normal distribution, respectively, and EI(x) is the value of the expected improvement function at point x;

[0080] Update the proxy model: After each evaluation, the new performance data y new Feedback to the GP model to update the proxy model Gradually narrow the search space and approach the optimal architecture;

[0081] IV. Model Training and Deployment

[0082] 1. Model training

[0083] Data input: Use preprocessed dataset As the input data of the model, the goal is to predict the exact location of the insulation material P k ;

[0084] Training process: Use the optimal model architecture x finally selected * Perform multiple rounds of iterative training and adjust the model weight θ through the gradient descent algorithm;

[0085] Gradient update formula:

[0086]

[0087] Among them, θ t+1 is the updated parameter, θ t is the current parameter, α is the learning rate, is the gradient with respect to the parameter θ, is the loss function, P k is the actual location, To predict the location;

[0088] 2. Model Validation

[0089] Validation set test: Use validation set data Evaluate the performance of the model and calculate the accuracy of the model Accuracy(x * ) and recall rate Recall(x * );

[0090] Accuracy formula:

[0091]

[0092] Where Accuracy(x * ) is the accuracy, TP, TN, FP, and FN are the number of true positives, true negatives, false positives, and false negatives, respectively;

[0093] Error analysis: prediction results The actual result P k Perform error analysis and calculate the error mean E m and standard deviation σ e , in order to locate the systematic errors in the model;

[0094] Error mean formula:

[0095]

[0096] Among them, E m is the mean error, N I is the sample size, is the summation symbol, P k is the true value, is the predicted value;

[0097] 3. Model Deployment

[0098] Model integration: Integrate the trained model into the intelligent assembly system to process real-time image data and sensor data Output the assembly decision of insulation materials;

[0099] System Testing: Testing Model X in a Real Assembly Environment * Stability, ensuring that the model can respond in real time and make accurate decisions;

[0100] 5. Intelligent assembly and feedback optimization

[0101] 1. Real-time monitoring

[0102] Assembly monitoring: Real-time capture of image data during assembly process real and sensor data F real ,T real , input to the deep learning model x * Output the predicted insulation material location

[0103] Among them, I real represents the new image dataset after preprocessing, F real represents the normalized force sensor data set, T realRepresents the new temperature sensor data set after normalization;

[0104] Dynamic adjustment: based on the model’s prediction results Dynamically adjust assembly parameters A adj (the position of the connecting rod, the filling density of the insulation cotton board) to ensure the assembly accuracy;

[0105] 2. Feedback Learning

[0106] Data collection: Continuously collect new assembly data Especially data under different temperature and force conditions to enhance the adaptability of the model;

[0107] Online learning: The model performs online learning and self-optimization based on new data, and gradually updates the model parameters θ through incremental learning new , further improving the performance of the model;

[0108] Online learning update formula:

[0109]

[0110] Among them, θ t+1 is the updated model parameter, θ t is the current model parameter, η is the learning rate, is the gradient with respect to the parameter θ, is the loss function, P new is the target location of the new dataset, For the predicted location.

[0111] Compared with the prior art, the present invention provides thermal insulation brickwork and a manufacturing method thereof, which have the following beneficial effects:

[0112] 1. The thermal insulation brickwork and its manufacturing method form an effective thermal insulation space inside the brick body by designing the bearing plate and the edge sealing plate. At the same time, the parallel arrangement and mutual contact of the edge sealing plate and the brickwork frame ensure the tightness and sealing of the structure and reduce the thermal bridge effect. The manufacturing process of the thermal insulation brickwork is relatively simple, and mass production can be achieved through reasonable mold design and casting process. At the same time, its multi-level protection design is also convenient for later maintenance.

[0113] 2. The thermal insulation brickwork and its manufacturing method are designed with a bearing plate and a connection frame inside the brick body, wherein the connection frame is filled with nano coils and thermal insulation cotton boards. These high-efficiency thermal insulation materials can significantly reduce heat transfer and improve the thermal insulation performance of the brickwork, thereby reducing the energy consumption of the building.

[0114] 3. The thermal insulation brickwork and its manufacturing method, by arranging reinforcing ribs and a support frame on the outside of the bearing plate, and wrapping the brickwork frame on the surface of the reinforcing ribs and the attachment rods by pouring and solidifying, this structure not only enhances the overall strength of the brickwork, but also improves its anti-deformation ability, thereby ensuring the stability of the brickwork during use.

[0115] 4. The thermal insulation brickwork and its manufacturing method not only enhance the fixation of the nano coil and the thermal insulation cotton board through the connecting rod designed inside the connecting frame, but also further enhance the stability of the entire structure by penetrating the supporting frame and extending into the interior thereof.

[0116] 5. The thermal insulation brickwork and its manufacturing method are characterized by arranging an insulating layer and a protective layer on the outside of the brickwork frame, wherein the insulating layer includes a waterproof coating and an outer layer plate, which effectively prevents water penetration from damaging the internal thermal insulation material; the protective layer provides additional protection through plastic film and sunscreen coating, thereby extending the service life of the brickwork.

[0117] 6. The thermal insulation brickwork and the manufacturing method thereof use thermal insulation resin materials as the main materials of the bearing plate, the edge sealing plate and the supporting frame. These materials not only have good thermal insulation performance, but also have sufficient strength and durability.

[0118] 7. By introducing an intelligent assembly algorithm based on deep learning, the system can monitor and accurately locate the position of insulation materials and their fixing components in real time, ensuring high precision and consistency of assembly.

[0119] 8. Through the real-time monitoring and feedback mechanism of intelligent algorithms, combined with data from visual sensors and force sensors, the system can dynamically adjust filling parameters to ensure tight filling and uniform distribution of insulation materials, thereby improving consistency and stability during the assembly process. BRIEF DESCRIPTION OF THE DRAWINGS

[0120] Figure 1 It is a structural schematic diagram of the present invention;

[0121] Figure 2 It is a schematic diagram of the top view structure of the present invention;

[0122] Figure 3 It is a schematic diagram of the three-dimensional structure separation of the present invention;

[0123] Figure 4 It is a three-dimensional schematic diagram of the local structure of the present invention;

[0124] Figure 5 It is a structural schematic diagram of the bearing plate of the present invention;

[0125] Figure 6 For the present invention Figure 2 The structural diagram of part A in the figure;

[0126] Figure 7 Flowchart of the neural architecture search and Bayesian optimization algorithm in the present invention.

[0127] In the figure: 1. Brick body; 2. Brickwork frame; 3. Load-bearing plate; 4. Edge banding plate; 5. Reinforcement ribs; 6. Attachment rods; 7. Support frame; 8. Connection frame; 9. Nano coil; 10. Insulation wool board; 11. Connection rod; 12. Nut; 13. Insulation layer; 14. Protective layer; 15. Waterproof coating; 16. Outer board; 17. Plastic film; 18. Sunscreen paint; 19. Connection hole; 20. Positioning rod; 21. Rock wool board. DETAILED DESCRIPTION

[0128] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention; it is obvious that the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments, and all other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making creative work are within the scope of protection of the present invention.

[0129] Embodiment 1:

[0130] Reference Figure 1-6, thermal insulation brickwork and its manufacturing method, including a brick body 1, the brick body 1 is composed of two brickwork frames 2, a bearing plate 3 is arranged on the inner side of the brickwork frame 2, there is a gap on the inner side of the bearing plate 3, the two ends of the bearing plate 3 extend to the two sides of the brickwork frame 2 respectively and are fixedly connected with edge sealing plates 4, the edge sealing plates 4 and the brickwork frame 2 are parallel to each other, the inner side of the edge sealing plates 4 is in contact with the surface of the brickwork frame 2, the edge sealing plates 4 and the bearing plates 3 are both made of thermal insulation resin material, the outer side of the bearing plate 3 is fixedly connected with a reinforcing rib 5, the side of the reinforcing rib 5 away from the bearing plate 3 extends to the inside of the brickwork frame 2, the inner side of the reinforcing rib 5 is fixedly connected with an attachment rod 6 located inside the brickwork frame 2, the brickwork frame 2 is wrapped around the surface of the reinforcing rib 5 and the attachment rod 6 by pouring and solidification, the outer side of the bearing plate 3 is fixedly connected with a supporting frame 7, the side of the supporting frame 7 away from the bearing plate 3 is in contact with the inner side of the brickwork frame 2, the material of the supporting frame 7 is a resin material, the bearing plate 3 A connecting frame 8 is provided on the inner side, and the interior of the connecting frame 8 is filled with thermal insulation material, which includes nano coils 9 filled in the connecting frame 8, and thermal insulation cotton boards 10 located in the connecting frame 8 are provided on both sides of the nano coils 9, and connecting rods 11 are provided at the four corners of the connecting frame 8. The nano coils 9 are wrapped on the surface of the connecting rods 11, and both ends of the connecting rods 11 successively penetrate the thermal insulation cotton board 10, the connecting frame 8, the bearing plate 3 and the support frame 7 and extend to the interior of the support frame 7, and both ends of the connecting rods 11 are threadedly connected with nuts 12 located in the support frame 7, an insulating layer 13 is provided on the outer side of the brickwork frame 2, and a protective layer 14 is provided on the outer side of the insulating layer 13, and the insulating layer 13 includes a waterproof coating 15 coated on the outer side of the brickwork frame 2, and an outer layer board 16 is adhered to the surface of the waterproof coating 15, and the protective layer 14 includes a plastic film 17 fixedly connected to the surface of the outer layer board 16, and the surface of the plastic film 17 is coated with a sunscreen coating 18.

[0131] Thermal insulation brickwork and a method for manufacturing the same comprise the following steps:

[0132] S1: According to the design size of the thermal insulation brickwork, prepare corresponding molds, including molds for the brickwork frame 2 and molds for components such as the bearing plate 3 and the edge plate 4, and use thermal insulation resin materials to injection mold the bearing plate 3 and the edge plate 4 as well as the reinforcing ribs 5 and the attachment rods 6 on both sides in the mold, ensuring that there is enough space inside the bearing plate 3 for subsequent filling of thermal insulation materials;

[0133] S2: After the bearing plate 3 and the edge plate 4 are formed, necessary trimming and inspection are carried out to ensure that the size and shape meet the design requirements. When the bearing plate 3 is processed, the support frame 7 is fixedly connected to the outside of the bearing plate 3 and the bearing plate 3 together with the edge plate 4 are moved to the inside of the bricklaying frame 2 mold, ensuring that the edge plate 4 and the bricklaying frame 2 mold are parallel to each other, and the inner side is in close contact with the mold surface, and the casting material of the bricklaying frame 2, such as concrete or other suitable materials, is poured into the mold, so that the casting material completely fills the gap between the support frame 7 and the mold, and the material fully wraps the reinforcing ribs 5 and the attachment rods 6, and waits for the casting material to solidify and form the bricklaying frame 2;

[0134] S3: Install a connecting frame 8 on the inner side of the supporting plate 3, and fill the connecting frame 8 with nano coils 9 and thermal insulation cotton boards 10. Use a connecting rod 11 to penetrate the thermal insulation cotton boards 10, the connecting frame 8, the supporting plate 3 and the supporting frame 7, and install a nut 12 inside the supporting frame 7 to fix the connecting rod 11 and the thermal insulation material.

[0135] S4: A waterproof coating 15 is applied on the outer side of the brickwork frame 2 to form an insulating layer 13. After the waterproof coating 15 is dried, an outer plate 16 is adhered to the surface of the waterproof coating 15 and a plastic film 17 is attached to the surface of the outer plate 16. At the same time, a sunscreen coating 18 is applied on the surface of the plastic film 17 to form a protective layer 14, thereby completing the production of thermal insulation blocks.

[0136] In step S3, in order to ensure the accurate filling and fixation of the thermal insulation material, it is proposed to adopt an intelligent assembly algorithm; the specific implementation process is as follows:

[0137] 1. Data Collection and Preprocessing

[0138] For example, the image data is I1(100,150)=200, which means that the pixel value of the 100th row and the 150th column is 200. The force measured by the force sensor is F1=150N, the temperature measured by the temperature sensor is T1=25°C, and the data range is -20 to 5°C.

[0139] Image Normalization:

[0140]

[0141] 2. Automatically Design Deep Learning Models Using NAS

[0142] Convolutional layer configuration

[0143] Assume that the number of convolutional layers is N c =2, the convolution kernel size is K c =3×3, stride S c =1, fill mode is "same"

[0144] Assume that the weight matrix W1 of the convolution kernel is:

[0145]

[0146] Convolution operation result:

[0147]

[0148] Pooling layer configuration

[0149] Assume the number of pooling layers N p =1, pooling window size K p =2×2, stride S p =2. Maximum pooling result:

[0150] O p,1 (50,75)

[0151] =max{O c,1 (100,150),O c,1 (100,151),O c,1 (101,150),O c,1 (101,151)}Fully connected layer configuration

[0152] Assume that the number of nodes in the fully connected layer is N fc =256, and the activation function is ReLU.

[0153] Output of the fully connected layer:

[0154]

[0155] Search algorithm selection

[0156] Update using reinforcement learning policy:

[0157] θ t+1 =θ t +0.01×0.5×Reward=θ t +0.005×Reward

[0158] The fitness function using the evolutionary algorithm is:

[0159] f(x)=0.9-0.01×0.2=0.898

[0160] 3. Combining Bayesian Optimization to Accelerate Architecture Search

[0161] Introduction to Bayesian Optimization

[0162] Calculate using Gaussian process kernel function:

[0163] The kernel function is:

[0164]

[0165] Optimization process

[0166] Use the EI strategy to select the next set of architectures:

[0167] The EI strategy is:

[0168]

[0169] 4. Model Training and Deployment

[0170] Model Training

[0171] Assume that the learning rate of gradient descent is α=0.001 and the loss function is the mean square error L.

[0172] Training Update:

[0173]

[0174] Model Validation

[0175] Accuracy calculation:

[0176] Assuming TP=90,TN=80,FP=10,FN=20, the accuracy is:

[0177]

[0178] 5. Intelligent assembly and feedback optimization

[0179] Real-time prediction of assembly location:

[0180] Assume the predicted position:

[0181]

[0182] Feedback Learning:

[0183]

[0184] By optimizing the insulation material filling and fixing system, the following specific numerical results were obtained:

[0185] Positioning error: 2.24 pixels, indicating that the system can locate the insulation material with high precision.

[0186] Filling error: 0.02, indicating that the filling density basically meets the expected standard.

[0187] Force error: 2N, indicating that the system maintains good mechanical stability during the assembly process.

[0188] Temperature error: 0.2℃, indicating that the system is stable in temperature control.

[0189] Improved assembly efficiency: The assembly time was shortened by 10%, indicating that the production efficiency of the system was improved.

[0190] Embodiment 2:

[0191] Reference Figure 1 and Figure 6 The thermal insulation brickwork and the manufacturing method thereof are basically the same as those in Example 1. Furthermore, connection holes 19 are provided on both sides of the top and bottom of the brickwork frame 2, and a positioning rod 20 is inserted into the interior of the connection hole 19. The interior of the support frame 7 is filled with a rock wool board 21, and a protrusion is provided on the inner side of the rock wool board 21, and the protrusion extends from the side away from the rock wool board 21 to the inner side of the connecting rod 11.

[0192] By setting the connecting hole 19 and the positioning rod 20, the connection efficiency of the brick body 1 can be improved and the brick body 1 can be prevented from tilting, and the rock wool board 21 can further improve the thermal insulation effect. At the same time, the raised portion on the inner side of the rock wool board 21 can extend to the inner side of the connecting rod 11. The installed connecting rod 11 can effectively fix the rock wool board 21 to prevent the rock wool board 21 from separating from the support frame 7.

[0193] Specifically, when the thermal insulation brickwork is working / in use: the supporting plate 3 and the edge sealing plate 4 are both made of insulating resin material, which has good thermal insulation performance and can significantly reduce the heat transfer through the brick body 1, thereby maintaining the stability of the indoor temperature; the gap on the inner side of the supporting plate 3 forms an insulating space, which blocks the path of heat through direct conduction, further enhancing the thermal insulation effect; the connecting frame 8 on the inner side of the supporting plate 3 is filled with nano coils 9 and thermal insulation cotton boards 10, which are high-efficiency thermal insulation materials with excellent thermal insulation performance and can effectively prevent the transfer of heat; the high-performance thermal insulation characteristics of the nano coils 9 and the good thermal insulation effect of the thermal insulation cotton boards 10 are combined to make the thermal insulation performance of the entire thermal insulation brickwork more superior; the reinforcing ribs 5 and the attachment rods 6 not only enhance the structural strength of the brickwork frame 2, but also form a stable supporting structure by extending and wrapping the brickwork frame 2; this structural support helps to maintain the overall shape and stability of the thermal insulation brickwork, thereby avoiding the degradation of thermal insulation performance due to deformation.

[0194] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A thermal insulation brickwork comprising a brick body (1), characterized in that: The brick body (1) is composed of two bricklaying frames (2), a bearing plate (3) is arranged on the inner side of the bricklaying frame (2), a gap is present on the inner side of the bearing plate (3), two ends of the bearing plate (3) respectively extend to the two sides of the bricklaying frame (2) and are fixedly connected with an edge sealing plate (4), the edge sealing plate (4) and the bricklaying frame (2) are parallel to each other, the inner side of the edge sealing plate (4) is in contact with the surface of the bricklaying frame (2), and the edge sealing plate (4) and the bearing plate (3) are both made of heat-insulating resin material.

2. The thermal insulation brickwork according to claim 1, characterized in that: The outer side of the bearing plate (3) is fixedly connected with a reinforcing rib (5), and the reinforcing rib (5) extends to the inside of the bricklaying frame (2) from a side away from the bearing plate (3). The inner side of the reinforcing rib (5) is fixedly connected with an attachment rod (6) located inside the bricklaying frame (2), and the bricklaying frame (2) is wrapped around the surface of the reinforcing rib (5) and the attachment rod (6) by pouring and solidifying.

3. The thermal insulation brickwork according to claim 1, characterized in that: A support frame (7) is fixedly connected to the outer side of the bearing plate (3); a side of the support frame (7) away from the bearing plate (3) contacts the inner side of the bricklaying frame (2); and the support frame (7) is made of resin material.

4. The thermal insulation brickwork according to claim 2, characterized in that: A connection frame (8) is provided on the inner side of the bearing plate (3), and the interior of the connection frame (8) is filled with heat-insulating material.

5. The thermal insulation brickwork according to claim 4, characterized in that: The heat-insulating material comprises a nano coil (9) filled in a connection frame (8), and heat-insulating cotton boards (10) located in the connection frame (8) are arranged on both sides of the nano coil (9).

6. The thermal insulation brickwork according to claim 5, characterized in that: Connecting rods (11) are provided at the four corners inside the connecting frame (8), the nano coil (9) is wrapped around the surface of the connecting rod (11), both ends of the connecting rod (11) successively penetrate the thermal insulation cotton board (10), the connecting frame (8), the bearing plate (3) and the support frame (7) and extend to the inside of the support frame (7), and both ends of the connecting rod (11) are threadedly connected to nuts (12) located inside the support frame (7).

7. The thermal insulation brickwork according to claim 1, characterized in that: An insulating layer (13) is arranged on the outer side of the brickwork frame (2), and a protective layer (14) is arranged on the outer side of the insulating layer (13). The insulating layer (13) comprises a waterproof coating (15) coated on the outer side of the brickwork frame (2), and an outer layer board (16) is adhered to the surface of the waterproof coating (15). The protective layer (14) comprises a plastic film (17) fixedly connected to the surface of the outer layer board (16), and the surface of the plastic film (17) is coated with a sunscreen paint (18).

8. The method for manufacturing thermal insulation brickwork according to any one of the above claims, characterized in that: The following steps are involved: S1: According to the design size of the thermal insulation brickwork, corresponding molds are prepared, including molds for the brickwork frame (2) and molds for components such as the bearing plate (3) and the edge plate (4). The bearing plate (3) and the edge plate (4) as well as the reinforcing ribs (5) and the attachment rods (6) on both sides are injection molded in the mold using a thermal insulation resin material, ensuring that sufficient space is left inside the bearing plate (3) so that the thermal insulation material can be filled in later. S2: After the bearing plate (3) and the edge plate (4) are formed, necessary trimming and inspection are carried out to ensure that the size and shape meet the design requirements. When the bearing plate (3) is processed, the support frame (7) is fixedly connected to the outer side of the bearing plate (3) and the bearing plate (3) together with the edge plate (4) are moved to the inside of the bricklaying frame (2) mold, ensuring that the edge plate (4) and the bricklaying frame (2) mold are parallel to each other and the inner side is in close contact with the mold surface. The casting material (such as concrete or other suitable material) of the bricklaying frame (2) is poured into the mold so that the casting material completely fills the gap between the support frame (7) and the mold, and the material fully wraps the reinforcing ribs (5) and the attachment rods (6). Wait for the casting material to solidify and form the bricklaying frame (2); S3: installing a connection frame (8) on the inner side of the bearing plate (3), and filling the connection frame (8) with nano coils (9) and thermal insulation cotton boards (10), using a connection rod (11) to penetrate the thermal insulation cotton boards (10), the connection frame (8), the bearing plate (3) and the support frame (7), and installing a nut (12) inside the support frame (7) to fix the connection rod (11) and the thermal insulation material; S4: A waterproof coating (15) is applied on the outer side of the brickwork frame (2) to form an insulating layer (13). After the waterproof coating (15) is dried, an outer plate (16) is adhered to the surface of the waterproof coating (15) and a plastic film (17) is attached to the surface of the outer plate (16). At the same time, a sunscreen coating (18) is applied on the surface of the plastic film (17) to form a protective layer (14), thereby completing the production of thermal insulation blocks.

9. The method for manufacturing thermal insulation brickwork according to claim 8, characterized in that: Step S3 also includes using an intelligent assembly algorithm to ensure accurate filling and fixing of the insulation material. The specific implementation process is as follows:

1. Data Collection and Preprocessing 1. Sensor placement Visual sensor: High-resolution industrial cameras are placed at key locations on the assembly line to capture real-time images of insulation materials during assembly; the collected image data is represented as variable I k , where k represents the sequence number of the acquired image; Force sensor: Force sensors are arranged at the contact parts such as connecting rods, nano coils, and thermal insulation cotton boards to monitor the force conditions of each component during the assembly process; the data of the force sensor is expressed as a variable F i , where i represents the number of the force sensor; Temperature sensor: Arrange temperature sensors in the assembly environment to monitor the impact of ambient temperature on the filling and fixing of insulation materials; temperature data is represented by variable T j , where j represents the number of the temperature sensor; 2. Data collection and annotation Image data acquisition: The image data of the insulation material assembly process is collected in real time through visual sensors. The image data acquisition frequency is f I , the collected data set is represented as Where N I is the total number of image data; Force and temperature data acquisition: Synchronously collect data from force sensors and temperature sensors. The force sensor data set is represented as The temperature sensor dataset is represented as Where N F and N T are the total number of force and temperature data, respectively; Data annotation: Annotate the collected images and sensor data, including the specific location of the components. k , Size S k , filling density D k , stress state F i and temperature state T j ; 3. Data Preprocessing Image preprocessing: collect image data k After processing, the image data is represented by image enhancement, size scaling, and noise filtering. Data normalization: force data F i and temperature data T j Normalization is performed to eliminate dimension differences; the normalization formula is as follows: Normalize the image data: Among them, I k (x,y) is the original image I k The pixel value at position (x, y), I min and I max are the minimum and maximum values ​​of the image pixels, respectively. is the pixel value of the normalized image data at position (x, y); Normalize the force sensor data: in, is the value of the normalized force sensor data, F i is the measured value of the original force sensor at a certain moment, F min is the minimum value of the force sensor data, F max is the maximum value of the force sensor data; Normalize the temperature sensor data: in, is the value of the normalized temperature sensor data, T j is the measurement value of the original temperature sensor at a certain moment, T min is the minimum value of the temperature sensor data, T max is the maximum value of the temperature sensor data; 2. Automatically Design Deep Learning Models Using NAS 1. Search space definition Convolutional layer configuration: defines the parameters of the convolutional layer, including the convolution kernel size, stride, padding method, and number of convolutional layers; The output formula of the convolutional layer is: in, c represents the convolutional layer, K c is the convolution kernel size, S c is the stride length, P c is the filling method, N c is the number of convolutional layers, W l is the weight matrix of the convolution kernel, b l is the bias term, O c,l is the output representation of each convolutional layer, l is the index of the convolutional layer, and m and n are variables used to index the elements inside the convolution kernel or pooling window; Pooling layer configuration: defines the parameters of the pooling layer, including the pooling window size K p , stride S p And the number of pooling layers N p ; The output of the pooling layer is represented as O p,m ; The output formula of the maximum pooling layer is: Among them, p represents the pooling layer, O p,m (x, y) This is the output value corresponding to the position (x, y) in the pooling layer m, max means taking the maximum value, i and j are the indexes inside the pooling window, and Kp is the size of the pooling window; Fully connected layer configuration: defines the parameters of the fully connected layer, including the number of nodes N fc , activation function σ fc , and the number of fully connected layers L fc ; The output of the fully connected layer is represented as O fc,n , where n is the index of the fully connected layer; The output formula of the fully connected layer is: Among them, fc represents the fully connected layer, O fc,n represents the value of the nth output node in the fully connected layer, σ fc is the activation function used by the fully connected layer, ∑ o represents the weighted sum of all inputs, O p,m (p) represents the value of the mth output node at index p in the previous layer, W fc,n is the weight matrix of the fully connected layer, b fc,n is the bias term; 2. Search algorithm selection NAS based on reinforcement learning: In this step, the NAS algorithm based on reinforcement learning is used; the parameters of the policy network are θ, the parameters of the agent network are φ, and the action sequence used is a t , the state is s t , then the policy network updates the parameters by maximizing the following objectives: Reinforcement learning strategy update formula: Among them, θ t+1 is the updated policy parameter, θ t is the strategy parameter at the current moment, is the policy gradient, α is the learning rate, R t is the return value, π θ is a policy controlled by parameter θ; Evolutionary Algorithm NAS: In the evolutionary algorithm, each individual in the population represents a model architecture; the fitness function f(x) of the population contains a trade-off between accuracy and complexity, and the fitness function is defined as: Fitness function formula: f(x)=Accuracy(x)-λ·Complexity(x) Among them, f(x) is the value of the fitness function, λ is the trade-off coefficient, Accuracy(x) represents the accuracy of the model, and Complexity(x) is the complexity of the model; 3. Search process Training model: During the search process, use the collected data set Train each model architecture generated by NAS and output the predicted insulation material positioning results Evaluate the model: Use the validation dataset to calculate the accuracy of each architecture Accuracy(x) and select the best model architecture x based on the fitness function * ; Model selection: Finally, the model architecture x with the largest fitness function value f(x) is selected * As the final architecture, and ready for further optimization; 3. Combining Bayesian Optimization to Accelerate Architecture Search 1. Introduction of Bayesian Optimization Surrogate model selection: Use Gaussian process (GP) as the surrogate model for Bayesian optimization. The kernel function of the surrogate model is represented by k(x, x') to model the performance distribution of the NAS search space. Gaussian process kernel function formula: Among them, k(x,x') is the kernel function in the Gaussian process, is the kernel function amplitude, l is the kernel function scale, x and x' are different architecture parameters, exp is the exponential function; 2. Optimization process Sampling and Inference: Use GP to infer the distribution of the current optimal architecture parameters and use the expected improvement (EI) strategy to select the next set of architecture parameters x to be evaluated. next ; Expected Improvement (EI) Strategy Formula: Where μ(x) is the predicted mean of the GP model, σ(x) is the predicted variance, τ is the current best value, Φ and φ are the cumulative distribution function and probability density function of the standard normal distribution, respectively, and EI(x) is the value of the expected improvement function at point x; Update the proxy model: After each evaluation, the new performance data y new Feedback to the GP model to update the proxy model Gradually narrow the search space and approach the optimal architecture; IV. Model Training and Deployment 1. Model training Data input: Use preprocessed dataset As the input data of the model, the goal is to predict the exact location of the insulation material P k ; Training process: Use the optimal model architecture x finally selected * Perform multiple rounds of iterative training and adjust the model weight θ through the gradient descent algorithm; Gradient update formula: Among them, θ t+1 is the updated parameter, θ t is the current parameter, α is the learning rate, is the gradient with respect to the parameter θ, is the loss function, P k is the actual location, To predict the location; 2. Model Validation Validation set test: Use validation set data Evaluate the performance of the model and calculate the accuracy of the model Accuracy(x * ) and recall rate Recall(x * ); Accuracy formula: Where Accuracy(x * ) is the accuracy, TP, TN, FP, and FN are the number of true positives, true negatives, false positives, and false negatives, respectively; Error analysis: prediction results The actual result P k Perform error analysis and calculate the error mean E m and standard deviation σ e , in order to locate the systematic errors in the model; Error mean formula: Among them, E m is the mean error, N I is the sample size, is the summation symbol, P k is the true value, is the predicted value; 3. Model Deployment Model integration: Integrate the trained model into the intelligent assembly system to process real-time image data and sensor data Output the assembly decision of insulation materials; System Testing: Testing Model X in a Real Assembly Environment * Stability, ensuring that the model can respond in real time and make accurate decisions; 5. Intelligent assembly and feedback optimization 1. Real-time monitoring Assembly monitoring: Real-time capture of image data during assembly process real and sensor data F real ,T real , input to the deep learning model x * Output the predicted insulation material location in, I rael represents the new image dataset after preprocessing, F real represents the normalized force sensor data set, T real Represents the new temperature sensor data set after normalization; Dynamic adjustment: based on the model’s prediction results Dynamically adjust assembly parameters A adj (the position of the connecting rod, the filling density of the insulation cotton board) to ensure the assembly accuracy; 2. Feedback Learning Data collection: Continuously collect new assembly data Especially data under different temperature and force conditions to enhance the adaptability of the model; Online learning: The model performs online learning and self-optimization based on new data, and gradually updates the model parameters θ through incremental learning new , further improving the performance of the model; Online learning update formula: Among them, θ t+1 is the updated model parameter, θ t is the current model parameter, η is the learning rate, is the gradient with respect to the parameter θ, is the loss function, P new is the target location of the new dataset, For the predicted location.

Images