Air conditioner control panel program variable simplification method based on deep learning

Abstract

The invention discloses an air conditioner control panel program variable simplification method based on deep learning, and the method comprises the following steps: S1, collecting air conditioner control panel program variable data and operation environment data, carrying out the preprocessing, and constructing an original data set; s2, constructing a double-flow adaptive analysis architecture, and generating optimized weight distribution of program variables; s3, performing nonlinear adjustment on the optimization weight distribution of the program variables by utilizing a variant factor module through a dynamic variant mechanism to generate a program variable set; s4, generating a program variable removal or retention action based on a strategy network of an Actor-Critic structure, and generating a screened program variable set; s5, constructing a dependency topological graph, cutting redundant paths by using an improved minimum support tree algorithm, and generating a final simplified program variable set; and S6, automatically generating a new control logic program, and deploying the new control logic program to the air conditioner control panel. According to the method, the simplification of the program variables of the air conditioner control panel is realized by utilizing deep learning, a double-flow self-adaptive analysis architecture and a reinforcement learning strategy.

Description

Technical Field

[0001] The present invention relates to the technical field of air conditioning control, and in particular to a method for streamlining program variables of an air conditioning control panel based on deep learning. Background Art

[0002] With the development of modern air-conditioning technology, the air-conditioning control board, as the core component of air-conditioning equipment, carries multiple functions such as operating status monitoring, data processing, and control instruction execution. The embedded program of the air-conditioning control board usually contains a large number of variables. The design of these variables directly affects the storage efficiency, computing speed, and environmental adaptability of the control board program. However, in the development of existing air-conditioning control board programs, due to the lack of comprehensive analysis of the importance of variables and their dynamic characteristics, variable redundancy is relatively common. This not only takes up a lot of storage space, but also significantly reduces the program's operating efficiency and dynamic environmental adaptability, becoming an important issue that restricts the further improvement of air-conditioning performance.

[0003] At present, some existing technologies have proposed variable simplification and optimization methods to address the problem of program variable redundancy. For example, traditional static analysis methods simply sort the importance of variables by program call relationships and variable usage frequencies, and remove low-frequency variables based on threshold rules. However, such methods rely too much on manual experience and lack comprehensive consideration of the global importance of variables and adaptability to dynamic environments. In addition, static analysis methods cannot handle the complex correlation between variables and the external operating environment, resulting in unstable simplification results under diverse environmental conditions, and may even mistakenly delete key variables, thereby affecting the core control functions of the air conditioner.

[0004] Another type of technology uses heuristic algorithms to optimize program variables, such as using genetic algorithms, ant colony algorithms, etc. to perform global searches for optimization targets for variables. However, such algorithms usually require a lot of computing resources and are prone to falling into local optimal solutions. In addition, these heuristic methods often focus on modeling static relationships between variables, ignoring the weight changes of variables in a dynamic operating environment and the optimization of their adaptability to control logic. Especially in the case of multiple dynamic environmental factors such as temperature, humidity, and load involved in air-conditioning operation, the applicability of such algorithms is greatly limited.

[0005] In recent years, the rise of deep learning technology has provided new ideas for program variable optimization. Some studies have attempted to use deep neural networks to extract features and optimize program variables. However, existing deep learning-based methods generally adopt a single-stream global analysis architecture and lack fine-grained modeling of dynamic environments, resulting in a lack of robustness in the optimization results when facing complex environmental changes. In addition, these methods are mostly targeted at specific tasks and fail to form a closed loop of streamlining and optimization of the entire life cycle of program variables.

[0006] For the optimization of program variable dependencies, existing technologies usually use the minimum spanning tree algorithm or its variants to perform structured modeling and redundant path pruning between variables. However, these algorithms have significant defects in practical applications. On the one hand, the traditional minimum spanning tree algorithm only considers static weights when constructing dependencies, and fails to dynamically adjust the pruning threshold to adapt to the changes in the importance of program variables; on the other hand, these algorithms are too simple in their pruning strategies for low-weight paths and cannot distinguish the key dependencies that may be contained in low-weight paths, resulting in a lack of global coordination in the optimization results. In addition, these methods are prone to under-pruning or over-pruning in complex dependency topologies, which in turn affects the logical integrity and operating efficiency of the air-conditioning control panel.

[0007] In addition, in the process of generating and verifying the optimized program logic, most existing technologies use code generation methods based on manual configuration or simple template methods, which leads to a lack of flexibility and automation in the code generation process, and the performance of the optimized program cannot be fully verified. The operating environment of embedded systems is complex and resources are limited. The performance of the optimized program in terms of performance indicators such as storage efficiency, operating speed and response delay is crucial to the actual application of the control board, but the existing technology generally lacks systematic verification methods for these indicators and cannot fully measure the optimization effect. This further limits the application value of program optimization methods in the development of actual air-conditioning control boards.

[0008] Therefore, how to provide a method for streamlining air-conditioning control panel program variables based on deep learning is an issue that technicians in this field need to solve urgently. Summary of the invention

[0009] One purpose of the present invention is to propose a method for streamlining program variables of air-conditioning control panels based on deep learning. The present invention combines deep learning technology, dynamic variant mechanism, reinforcement learning strategy network and improved minimum spanning tree algorithm to streamline and optimize program variables of air-conditioning control panels, significantly improving program storage efficiency, running speed and dynamic environment adaptability. Through dual-stream adaptive analysis architecture and multi-dimensional weight optimization, the importance of variables is accurately evaluated; reinforcement learning dynamic adjustment strategy is used to intelligently remove redundant variables; through dependency topology modeling, redundant paths are cut, variable logical structure is optimized, and automatic generation and verification of control logic programs are realized, ensuring the efficiency, reliability and adaptability of the program.

[0010] The method for simplifying program variables of an air conditioning control panel based on deep learning according to an embodiment of the present invention comprises the following steps:

[0011] S1, collect the program variable data and operating environment data of the air conditioning control panel, perform preprocessing and construct the original data set;

[0012] S2. Construct a dual-stream adaptive analysis framework based on the original data set. The dual-stream adaptive analysis framework includes a main stream and an auxiliary stream. The main stream performs a global importance analysis on program variable data based on a variant network and uses a dynamic screening layer to quantify the importance score of program variable data. The auxiliary stream analyzes the weight changes of program variables under different operating environment characteristics based on dynamic environment modeling combined with a multi-head attention mechanism to generate an optimized weight distribution matrix of program variables.

[0013] S3, using a dynamic variant mechanism and a variant factor module to perform nonlinear adjustment on the optimized weight distribution matrix of program variables to generate a set of program variables;

[0014] S4, inputting the program variable set into the policy network based on the Actor-Critic structure to generate the action of removing or retaining the program variables, thereby generating a filtered program variable set;

[0015] S5. construct a dependency topology graph based on the screened program variable set and dependency relationships, and use an improved minimum spanning tree algorithm to cut redundant paths to generate a final streamlined program variable set;

[0016] S6. Automatically generate a new control logic program based on the final streamlined set of program variables, use embedded simulation tools to verify the storage efficiency, running speed and response delay performance of the new control logic program, and deploy the new control logic program to the air conditioning control board.

[0017] Optionally, the S2 specifically includes:

[0018] S21. In the mainstream, a variant network based on an improved residual network is used to perform global importance analysis on program variable data, wherein the variant network based on the improved residual network is composed of a plurality of residual modules, each residual module enhances the variable feature extraction capability through a jump connection, and extracts a preliminary program variable feature vector;

[0019] S22. Use the dynamic screening layer in the mainstream to perform quantitative analysis on the preliminary program variable feature vector. The dynamic screening layer calculates the importance score of the program variable in real time through the dynamic filtering module to generate a global importance score matrix:

[0020]

[0021] Among them, M s (i,j) represents the global importance score of the i-th program variable on the feature dimension of the k-th program variable, σ represents the activation function, N represents the number of feature maps in the dynamic screening layer, and λ in represents the weight of the i-th program variable on the n-th feature map, x i represents the eigenvalue of the i-th program variable, α nrepresents the nonlinear factor, ω n represents the frequency parameter on the nth feature map, f k represents the kth program variable feature dimension, θ n represents the phase shift on the nth feature map, exp represents the exponential function, μ n represents the time decay rate, and t represents the time step;

[0022] S23, in the auxiliary flow, the operating environment characteristics are analyzed based on dynamic environment modeling, and a multi-scale association between program variables and operating environment characteristics is established through environment labels and operating environment characteristic distribution;

[0023] S24. Use the multi-head attention mechanism to analyze the weight changes of program variables under different operating environments and generate a dynamic weight distribution matrix:

[0024]

[0025] Among them, W d (i,j) represents the weight of the i-th program variable on the j-th environmental feature dimension, a ij Represents program variable z i and environmental characteristics j The static association score, ρ m (z i ,e j ) represents the mth head in the multi-head attention mechanism for the program variable z i and environmental characteristics j The weight, ρ m (z p ,e j ) represents the mth head in the multi-head attention mechanism for the program variable z p and environmental characteristics j The weight, γ m represents the amplitude adjustment factor of the mth head, a pj represents the weight of the p-th program variable on the j-th environment feature dimension, h represents the number of heads of the multi-head attention mechanism, M represents the total number of program variables, and z i represents the ith program variable, z p represents the pth program variable, e j represents the jth environmental feature;

[0026] S25. Perform weighted fusion on the global importance score matrix generated by the mainstream and the dynamic weight distribution matrix generated by the auxiliary flow to calculate the optimized weight distribution matrix of the program variables:

[0027] P o (i,k,j)=β 1 ·ln(1+Ms (i,k) 2 )+β 2 ·W d (i,j);

[0028] Among them, P o (i, k, j) represents the optimization weight of the i-th program variable in the k-th program variable feature dimension and the j-th environment feature dimension, β 1 and β 2 Represents the weight distribution coefficient

[0029] S26. Output the optimized weight distribution matrix P of program variables o (i,k,j).

[0030] Optionally, the S3 specifically includes:

[0031] S31, construct a dynamic variant mechanism, the dynamic variant mechanism includes a dynamic perturbation module, a period adjustment module and a nonlinear weight optimization module, and uses the variant factor module to optimize the weight distribution matrix P of the program variables. o (i, k, j) performs dynamic nonlinear adjustment and calculates the optimized program variable weight matrix:

[0032]

[0033] Where Q(i,j) represents the optimization weight of the i-th program variable on the j-th environment feature dimension, K represents the total number of program variable feature dimensions, and η k Represents the weight adjustment coefficient for the kth program variable feature dimension in the variant factor module, ReLU represents the linear correction function, represents the perturbation factor of the kth program variable feature dimension, ω k represents the frequency parameter of the kth program variable feature dimension, θ k represents the phase shift of the kth program variable feature dimension, f k represents the kth program variable feature dimension, μ k Represents the decay rate of weight as the feature dimension changes, P o (i, k, j) represents the optimization weight of the i-th program variable in the k-th program variable feature dimension and the j-th environment feature dimension, and exp represents the exponential function;

[0034] The dynamic perturbation module is used to adjust the feature dimension f of the kth program variable k Introduce the perturbation factor of the kth program variable feature dimension Used to simulate the randomness of environmental changes during weight adjustment;

[0035] The periodic adjustment module uses the periodic adjustment function sin(ωk f k +θ k ) captures the periodic fluctuations of the characteristic dimensions of program variables;

[0036] The nonlinear weight optimization module uses the linear correction function ReLU and the dynamic attenuation function exp(-μ k f k ) realizes nonlinear adjustment of weight values;

[0037] S32, the dynamic variant mechanism dynamically extracts the program variable set by combining the optimized program variable weight matrix with the environmental characteristics:

[0038]

[0039] in, represents the characteristic value of the i-th program variable in the extracted program variable set, x i represents the initial characteristic value of the i-th program variable, and τ(j) represents the dynamic screening threshold of the j-th environmental feature dimension:

[0040]

[0041] Where M represents the total number of program variables, δ represents the dynamic screening sensitivity parameter, and Q mean Represents the mean of the optimized weights on the j-th environmental feature dimension.

[0042] Optionally, the S4 specifically includes:

[0043] S41, inputting the generated program variable set into a policy network based on an Actor-Critic structure, wherein the policy network includes an action generation module and a value evaluation module;

[0044] S42, in the action generation module, generating corresponding actions according to the current state of the program variable set, wherein the actions include a decision of removing or retaining each program variable;

[0045] S43, in the value evaluation module, the action generated by the action generation module is evaluated for value, and a comprehensive analysis is performed based on the state of the program variable set and the impact of the action on storage efficiency and program performance to generate a value evaluation result;

[0046] S44, optimizing the policy network through a policy optimization algorithm based on the actions generated by the action generation module and the value evaluation results of the value evaluation module;

[0047] S45, further screening the program variable set according to the optimized strategy network, removing unnecessary program variables, and retaining key program variables;

[0048] S46. Finally, a filtered program variable set is generated.

[0049] Optionally, the S5 specifically includes:

[0050] S51, receiving the filtered program variable set, constructing an initial variable dependency graph with the program variables as nodes, wherein the edges of the initial variable dependency graph represent functional correlations between the program variables;

[0051] S52. Calculate the weights of the edges in the initial variable dependency graph, and use a dynamic correlation analysis method to combine the mutual information of the variables and the call frequency to quantify the dependency weights:

[0052]

[0053] Among them, E(p,q) represents the program variable x p and the program variable x q The dependency weight between them, ζ represents the balance factor, I(x p ,x q ) represents the program variable x p and the program variable x q The mutual information value, F(x p ,x q ) represents the program variable x p and the program variable x q The number of joint calls of , T represents the total number of calls of the program variable;

[0054] S53, generating a variable dependency topology graph according to the calculated dependency weights, wherein the edge weights in the variable dependency topology graph represent the functional correlation between program variables, and modeling the structural relationship between program variables from a global perspective;

[0055] S54, based on the generated variable dependency topology graph, using an improved minimum spanning tree algorithm to prune redundant paths, wherein the improved minimum spanning tree algorithm includes: giving priority to edges with high weights during the calculation process to ensure that the core functional relationship between program variables is preserved; introducing a hierarchical screening mechanism to group dependency weights according to a dynamic range, and giving priority to pruning redundant paths in low-weight groups; and dynamically adjusting the pruning threshold in each iteration;

[0056] S55. Optimize the variable dependency topology graph pruned by the improved minimum spanning tree algorithm to generate a final streamlined set of program variables.

[0057] Optionally, the S6 specifically includes:

[0058] S61, receiving the final streamlined program variable set, and mapping it to the control logic template, and automatically generating a new control logic program according to the functional dependency relationship and operation logic of the program variables;

[0059] S62, inputting the new control logic program into an embedded simulation tool for simulation verification, where the simulation tool includes a storage efficiency module, an operation speed module, and a response delay module;

[0060] S63, using the storage efficiency module to calculate the storage occupancy rate of the new control logic program, comparing the storage usage before and after the optimization, and recording the storage efficiency improvement ratio;

[0061] S64, using the running speed module to measure the average execution time of the new control logic program under different workloads, and analyzing whether the processing performance of the program meets the running requirements of the air conditioning control board;

[0062] S65, using the response delay module to measure the time interval from the input signal to the generation of the output control signal of the new control logic program, to verify whether the real-time performance of the program meets the expected performance indicators;

[0063] S66. Deploy the new control logic program that has been verified by embedded simulation and meets the requirements of storage efficiency, operation speed and response delay to the air conditioning control board, and perform functional testing in the actual operating environment.

[0064] The beneficial effects of the present invention are:

[0065] First, the present invention realizes a multi-dimensional comprehensive evaluation of program variables under different operating environments through a dual-stream adaptive analysis architecture, combined with the global importance analysis of the mainstream and the dynamic environment modeling of the auxiliary stream. The mainstream uses an improved residual network to quantitatively analyze the global importance of variables, and the auxiliary stream uses a multi-head attention mechanism to dynamically model the weight changes of variables under different environmental characteristics, generating an optimized weight distribution matrix, thereby effectively solving the problem of the single-stream architecture in the prior art lacking the ability to model dynamic environments, and ensuring the stability and robustness of the variable simplification results.

[0066] Secondly, the dynamic variant mechanism of the present invention realizes the dynamic adjustment of program variable weights by introducing dynamic disturbance modules, periodic adjustment modules and nonlinear weight optimization modules. This mechanism can not only adapt to complex and changeable operating environments, but also make fine-grained adjustments to the weights of variables through nonlinear optimization, thereby improving the dynamic adaptability of program variable sets. Compared with the prior art method of relying on static rules to simplify variables, the present invention can more flexibly adjust the importance weights of variables, avoid mistaken deletion of key variables, and remove inefficient redundant variables, thereby achieving accurate optimization of program variable sets.

[0067] In addition, the reinforcement learning strategy network of the present invention uses the synergy of the action generation module and the value assessment module, and uses the optimization method based on the Actor-Critic structure to make intelligent decisions on the actions of removing or retaining program variables. The network balances the relationship between storage efficiency, program performance and environmental adaptability through the design of an adaptive reward function, solves the problem of the lack of intelligent dynamic optimization in the existing technology that simply relies on static analysis or heuristic algorithms, and significantly improves the automation and efficiency of variable simplification.

[0068] In terms of variable dependency optimization, the present invention constructs a dependency topology map based on dynamic correlation analysis, and uses an improved minimum spanning tree algorithm to prune redundant paths. The improved algorithm not only retains the core functional relationships in the variable set through a hierarchical screening mechanism and a dynamic pruning threshold adjustment strategy, but also effectively removes low-weight redundant paths and optimizes the global structure of the variable set. This method overcomes the problem that the traditional minimum spanning tree algorithm cannot dynamically adapt to changes in variable weights, and ensures that the streamlined variable set has higher functional integrity and logical coordination.

[0069] Finally, in the generation and verification stage of the control logic program, the present invention realizes the rapid generation of the optimized control logic program through an automated templated code generator, and uses an embedded simulation tool to comprehensively verify the program's performance indicators such as storage efficiency, running speed, and response delay. The simulation verification results provide a reliable basis for the actual deployment of the program, and further ensure the stability and adaptability of the program through actual operation tests in the hardware environment. Compared with the problem of lack of comprehensive verification means in the prior art, the present invention realizes efficient evaluation and performance guarantee of the optimized program, ensuring the reliability and superior performance of the program in a variety of complex operating environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0071] Figure 1 This is an overall flow chart of the method for streamlining program variables of an air-conditioning control panel based on deep learning proposed by the present invention;

[0072] Figure 2 This is a schematic diagram of the dual-stream adaptive analysis architecture structure of the air-conditioning control panel program variable simplification method based on deep learning proposed in the present invention. DETAILED DESCRIPTION

[0073] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, which only illustrate the basic structure of the present invention in a schematic manner, and therefore only show the components related to the present invention.

[0074] refer to Figure 1 and Figure 2 , the air conditioning control panel program variable simplification method based on deep learning includes the following steps:

[0075] S1, collect the program variable data and operating environment data of the air conditioning control panel, perform preprocessing and construct the original data set;

[0076] S2. Construct a dual-stream adaptive analysis framework based on the original data set. The dual-stream adaptive analysis framework includes a main stream and an auxiliary stream. The main stream performs a global importance analysis on program variable data based on a variant network and uses a dynamic screening layer to quantify the importance score of program variable data. The auxiliary stream analyzes the weight changes of program variables under different operating environment characteristics based on dynamic environment modeling combined with a multi-head attention mechanism to generate an optimized weight distribution matrix of program variables.

[0077] S3, using a dynamic variant mechanism and a variant factor module to perform nonlinear adjustment on the optimized weight distribution matrix of program variables to generate a set of program variables;

[0078] S4, inputting the program variable set into the policy network based on the Actor-Critic structure to generate the action of removing or retaining the program variables, thereby generating a filtered program variable set;

[0079] S5. construct a dependency topology graph based on the screened program variable set and dependency relationships, and use an improved minimum spanning tree algorithm to cut redundant paths to generate a final streamlined program variable set;

[0080] S6. Automatically generate a new control logic program based on the final streamlined set of program variables, use embedded simulation tools to verify the storage efficiency, running speed and response delay performance of the new control logic program, and deploy the new control logic program to the air conditioning control board.

[0081] In this implementation, S2 specifically includes:

[0082] S21. In the mainstream, a variant network based on an improved residual network is used to perform global importance analysis on program variable data, wherein the variant network based on the improved residual network is composed of a plurality of residual modules, each residual module enhances the variable feature extraction capability through a jump connection, and extracts a preliminary program variable feature vector;

[0083] S22. Use the dynamic screening layer in the mainstream to perform quantitative analysis on the preliminary program variable feature vector. The dynamic screening layer calculates the importance score of the program variable in real time through the dynamic filtering module to generate a global importance score matrix:

[0084]

[0085] Among them, M s (i,j) represents the global importance score of the i-th program variable on the feature dimension of the k-th program variable, σ represents the activation function, N represents the number of feature maps in the dynamic screening layer, and λ in represents the weight of the i-th program variable on the n-th feature map, x i represents the eigenvalue of the i-th program variable, α n represents the nonlinear factor, ω n represents the frequency parameter on the nth feature map, f k represents the kth program variable feature dimension, θ n represents the phase shift on the nth feature map, exp represents the exponential function, μ n represents the time decay rate, and t represents the time step;

[0086] S23, in the auxiliary flow, the operating environment characteristics are analyzed based on dynamic environment modeling, and a multi-scale association between program variables and operating environment characteristics is established through environment labels and operating environment characteristic distribution;

[0087] S24. Use the multi-head attention mechanism to analyze the weight changes of program variables under different operating environments and generate a dynamic weight distribution matrix:

[0088]

[0089] Among them, W d (i,j) represents the weight of the i-th program variable on the j-th environmental feature dimension, a ij Represents program variable z i and environmental characteristics j The static association score, ρ m (z i ,e j ) represents the mth head in the multi-head attention mechanism for the program variable z i and environmental characteristics j The weight, ρ m (z p ,e j ) represents the mth head in the multi-head attention mechanism for the program variable z p and environmental characteristics j The weight, γ m represents the amplitude adjustment factor of the mth head, apj represents the weight of the p-th program variable on the j-th environment feature dimension, h represents the number of heads of the multi-head attention mechanism, M represents the total number of program variables, and z i represents the ith program variable, z p represents the pth program variable, e j represents the jth environmental feature;

[0090] S25. Perform weighted fusion on the global importance score matrix generated by the mainstream and the dynamic weight distribution matrix generated by the auxiliary flow to calculate the optimized weight distribution matrix of the program variables:

[0091] P o (i,k,j)=β 1 ·ln(1+M s (i,k) 2 )+β 2 ·W d (i,j);

[0092] Among them, P o (i, k, j) represents the optimization weight of the i-th program variable in the k-th program variable feature dimension and the j-th environment feature dimension, β 1 and β 2 Represents the weight distribution coefficient

[0093] S26. Output the optimized weight distribution matrix P of program variables o (i,k,j).

[0094] In this implementation, S3 specifically includes:

[0095] S31, construct a dynamic variant mechanism, the dynamic variant mechanism includes a dynamic perturbation module, a period adjustment module and a nonlinear weight optimization module, and uses the variant factor module to optimize the weight distribution matrix P of the program variables. o (i, k, j) performs dynamic nonlinear adjustment and calculates the optimized program variable weight matrix:

[0096]

[0097] Where Q(i,j) represents the optimization weight of the i-th program variable on the j-th environment feature dimension, K represents the total number of program variable feature dimensions, and η k Represents the weight adjustment coefficient for the kth program variable feature dimension in the variant factor module, ReLU represents the linear correction function, represents the perturbation factor of the kth program variable feature dimension, ω k represents the frequency parameter of the kth program variable feature dimension, θ k represents the phase shift of the kth program variable feature dimension, fk represents the kth program variable feature dimension, μ k Represents the decay rate of weight as the feature dimension changes, P o (i, k, j) represents the optimization weight of the i-th program variable in the k-th program variable feature dimension and the j-th environment feature dimension, and exp represents the exponential function;

[0098] The dynamic perturbation module is used to adjust the feature dimension f of the kth program variable k Introduce the perturbation factor of the kth program variable feature dimension Used to simulate the randomness of environmental changes during weight adjustment;

[0099] The periodic adjustment module uses the periodic adjustment function sin(ω k f k +θ k ) captures the periodic fluctuations of the characteristic dimensions of program variables;

[0100] The nonlinear weight optimization module uses the linear correction function ReLU and the dynamic attenuation function exp(-μ k f k ) realizes nonlinear adjustment of weight values;

[0101] S32, the dynamic variant mechanism dynamically extracts the program variable set by combining the optimized program variable weight matrix with the environmental characteristics:

[0102]

[0103] in, represents the characteristic value of the i-th program variable in the extracted program variable set, x i represents the initial characteristic value of the i-th program variable, and τ(j) represents the dynamic screening threshold of the j-th environmental feature dimension:

[0104]

[0105] Where M represents the total number of program variables, δ represents the dynamic screening sensitivity parameter, and Q mean Represents the mean of the optimized weights on the j-th environmental feature dimension.

[0106] In this implementation, S4 specifically includes:

[0107] S41, inputting the generated program variable set into a policy network based on an Actor-Critic structure, wherein the policy network includes an action generation module and a value evaluation module;

[0108] S42, in the action generation module, generating corresponding actions according to the current state of the program variable set, wherein the actions include a decision of removing or retaining each program variable;

[0109] S43, in the value evaluation module, the action generated by the action generation module is evaluated for value, and a comprehensive analysis is performed based on the state of the program variable set and the impact of the action on storage efficiency and program performance to generate a value evaluation result;

[0110] S44, optimizing the policy network through a policy optimization algorithm based on the actions generated by the action generation module and the value evaluation results of the value evaluation module;

[0111] S45, further screening the program variable set according to the optimized strategy network, removing unnecessary program variables, and retaining key program variables;

[0112] S46. Finally, a filtered program variable set is generated.

[0113] In this implementation manner, S5 specifically includes:

[0114] S51, receiving the filtered program variable set, constructing an initial variable dependency graph with the program variables as nodes, wherein the edges of the initial variable dependency graph represent functional correlations between the program variables;

[0115] S52. Calculate the weights of the edges in the initial variable dependency graph, and use a dynamic correlation analysis method to combine the mutual information of the variables and the call frequency to quantify the dependency weights:

[0116]

[0117] Among them, E(p,q) represents the program variable x p and the program variable x q The dependency weight between them, ζ represents the balance factor, I(x p ,x q ) represents the program variable x p and the program variable x q The mutual information value, F(x p ,x q ) represents the program variable x p and the program variable x q The number of joint calls of T represents the total number of calls of the program variable;

[0118] S53, generating a variable dependency topology graph according to the calculated dependency weights, wherein the edge weights in the variable dependency topology graph represent the functional correlation between program variables, and modeling the structural relationship between program variables from a global perspective;

[0119] S54, based on the generated variable dependency topology graph, using an improved minimum spanning tree algorithm to prune redundant paths, wherein the improved minimum spanning tree algorithm includes: giving priority to edges with high weights during the calculation process to ensure that the core functional relationship between program variables is preserved; introducing a hierarchical screening mechanism to group dependency weights according to a dynamic range, and giving priority to pruning redundant paths in low-weight groups; and dynamically adjusting the pruning threshold in each iteration;

[0120] S55. Optimize the variable dependency topology graph pruned by the improved minimum spanning tree algorithm to generate a final streamlined set of program variables.

[0121] In this implementation manner, S6 specifically includes:

[0122] S61, receiving the final streamlined program variable set, and mapping it to the control logic template, and automatically generating a new control logic program according to the functional dependency relationship and operation logic of the program variables;

[0123] S62, inputting the new control logic program into an embedded simulation tool for simulation verification, where the simulation tool includes a storage efficiency module, an operation speed module, and a response delay module;

[0124] S63, using the storage efficiency module to calculate the storage occupancy rate of the new control logic program, comparing the storage usage before and after the optimization, and recording the storage efficiency improvement ratio;

[0125] S64, using the running speed module to measure the average execution time of the new control logic program under different workloads, and analyzing whether the processing performance of the program meets the running requirements of the air conditioning control board;

[0126] S65, using the response delay module to measure the time interval from the input signal to the generation of the output control signal of the new control logic program, to verify whether the real-time performance of the program meets the expected performance indicators;

[0127] S66. Deploy the new control logic program that has been verified by embedded simulation and meets the requirements of storage efficiency, operation speed and response delay to the air conditioning control board, and perform functional testing in the actual operating environment.

[0128] Embodiment 1:

[0129] In order to verify the feasibility of the present invention in implementation, the present invention is applied to a certain brand of household intelligent air-conditioning control system as a test platform. The air-conditioning control system contains multiple complex embedded programs with a large number of program variables, and the air-conditioning needs to maintain efficient operation under different environmental conditions. However, due to the variable redundancy problem, the existing control logic has obvious deficiencies in terms of storage space occupation, operating speed and environmental adaptability. The experiment aims to simplify and optimize the program variables of the air-conditioning control panel through the method of the present invention, and verify its improvement effect on the above-mentioned key performance indicators.

[0130] In this embodiment, the operating data and operating environment information of the air conditioning control panel are first collected, including temperature, humidity, operating mode (cooling, heating, dehumidification) and load conditions. The original data set contains 500 program variables and 10 different environmental characteristics, where the program variables record the sensor status, control logic instructions and energy consumption monitoring information of the air conditioner. After preprocessing, these data are constructed into a multidimensional original data set, which provides a basis for subsequent optimization.

[0131] Next, the original data was analyzed and processed using a two-stream adaptive analysis architecture. The main stream extracted the global importance score of program variables based on an improved residual network, and the auxiliary stream combined with a multi-head attention mechanism generated the dynamic weight distribution of variables under different environmental conditions. Through the joint modeling of the two-stream architecture, an optimized weight distribution matrix of program variables was generated, laying the foundation for dynamic adjustment and streamlining of program variables.

[0132] In the optimization process of the dynamic variant mechanism, the system uses the variant factor module to dynamically adjust the optimization weight distribution, and performs fine-grained nonlinear optimization on the importance and environmental adaptability of program variables. The optimized program variable set is input into the reinforcement learning strategy network based on the Actor-Critic structure. With the support of the intelligent decision-making mechanism, 100 redundant variables are removed to generate a streamlined program variable set.

[0133] Subsequently, the dependency topology modeling of the streamlined variable set was performed using the improved minimum spanning tree algorithm. The improved algorithm further optimized the structure of the program variable set by giving priority to retaining high-weight paths, introducing a hierarchical screening mechanism, and dynamically adjusting the pruning threshold. Finally, a final streamlined program variable set containing 200 core variables was generated, which was 60% less than the original variable set.

[0134] Finally, based on the streamlined set of program variables, the system automatically generated a new air-conditioning control logic program, and used embedded simulation tools to fully verify the program performance. The results showed that the optimized program has significantly improved storage space usage, running speed, and response delay performance. After actual operation tests, the optimized control logic has shown strong stability and environmental adaptability under various environmental conditions such as high temperature, high humidity, low load, and high load.

[0135] Table 1 Comparison of key performance indicators before and after air conditioning control panel program optimization

[0136]

[0137]

[0138] It can be seen from the data in Table 1 above that the optimization method of the present invention has shown significant advantages in multiple key performance indicators, which fully verifies its actual effect in the optimization of air-conditioning control panel programs.

[0139] First, in terms of the number of program variables, there were 500 variables before optimization, but only 200 variables after optimization, a 60% reduction in the number of variables. This shows that through the joint application of the dual-stream adaptive analysis architecture, dynamic variant mechanism and reinforcement learning strategy, a large number of redundant variables have been successfully removed, which greatly simplifies the program structure and lays the foundation for the release of storage space.

[0140] Secondly, the storage space usage is reduced from 1024KB before optimization to 512KB after optimization, a reduction of 50%. This result verifies the direct contribution of program variable simplification to the improvement of storage efficiency, and also shows that in embedded systems, the present invention can effectively reduce the storage burden of programs and is suitable for hardware environments with limited resources.

[0141] In terms of running speed, the average running time of the optimized program is 9.2 milliseconds, which is 41.77% higher than the 15.8 milliseconds before optimization. This improvement is due to the removal of redundant variables and the optimized variable logic structure, which greatly reduces the redundant calculations during program operation, thereby speeding up the processing speed and improving the system's responsiveness.

[0142] The response delay, an important performance indicator of the air conditioning control system, has also been significantly improved. The optimized response delay is 1.3 milliseconds, which is 48% less than the 2.5 milliseconds before optimization. This improvement shows that the present invention not only improves the program operation efficiency, but also significantly enhances the real-time performance of the air conditioning system, enabling it to respond quickly to user operations and environmental changes, thereby improving the user experience.

[0143] The environmental adaptability score increased from 6.8 points before optimization to 9.2 points after optimization, an increase of 35.29%. This data shows that through the multi-head attention mechanism and dynamic weight adjustment method, the program can better adapt to changes in dynamic environmental characteristics such as temperature, humidity and load. The optimized program can still maintain efficient operation under diverse working conditions, reflecting its strong environmental adaptability and robustness.

[0144] Finally, the average power consumption dropped from 85 watts before optimization to 78 watts, a reduction of 8.24%. This result shows that through variable reduction and logic optimization, not only the resource consumption of storage and computing is reduced, but also the overall power consumption of the system is reduced, making it more energy-efficient and environmentally friendly, providing support for the long-term and efficient operation of embedded devices.

[0145] This embodiment verifies the feasibility and effectiveness of the present invention in actual scenarios by applying it to a certain brand of household intelligent air-conditioning control system. The optimization results show that the present invention significantly reduces the number of program variables and storage space occupied, improves the program running speed and responsiveness, and enhances environmental adaptability and energy-saving effects. The data verifies the high efficiency and stability of the optimized program under various working conditions, and comprehensively solves the problems of low storage efficiency, poor operating performance and insufficient environmental adaptability caused by variable redundancy in traditional methods, providing a new technical path and practical basis for the optimization of smart homes and embedded systems.

[0146] 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 method for streamlining program variables of air-conditioning control panels based on deep learning, characterized in that: The steps include: S1, collect the program variable data and operating environment data of the air conditioning control panel, perform preprocessing and construct the original data set; S2. Construct a dual-stream adaptive analysis framework based on the original data set. The dual-stream adaptive analysis framework includes a main stream and an auxiliary stream. The main stream performs a global importance analysis on program variable data based on a variant network and uses a dynamic screening layer to quantify the importance score of program variable data. The auxiliary stream analyzes the weight changes of program variables under different operating environment characteristics based on dynamic environment modeling combined with a multi-head attention mechanism to generate an optimized weight distribution matrix of program variables. S3, using a dynamic variant mechanism and a variant factor module to perform nonlinear adjustment on the optimized weight distribution matrix of program variables to generate a set of program variables; S4, inputting the program variable set into the policy network based on the Actor-Critic structure to generate the action of removing or retaining the program variables, thereby generating a filtered program variable set; S5. construct a dependency topology graph based on the screened program variable set and dependency relationships, and use an improved minimum spanning tree algorithm to cut redundant paths to generate a final streamlined program variable set; S6. Automatically generate a new control logic program based on the final streamlined set of program variables, use embedded simulation tools to verify the storage efficiency, running speed and response delay performance of the new control logic program, and deploy the new control logic program to the air conditioning control board.

2. The method for simplifying program variables of an air-conditioning control panel based on deep learning according to claim 1, characterized in that: The S2 specifically includes: S21. In the mainstream, a variant network based on an improved residual network is used to perform global importance analysis on program variable data, wherein the variant network based on the improved residual network is composed of a plurality of residual modules, each residual module enhances the variable feature extraction capability through a jump connection, and extracts a preliminary program variable feature vector; S22. Use the dynamic screening layer in the mainstream to perform quantitative analysis on the preliminary program variable feature vector. The dynamic screening layer calculates the importance score of the program variable in real time through the dynamic filtering module to generate a global importance score matrix: Among them, M s (i,j) represents the global importance score of the i-th program variable on the feature dimension of the k-th program variable, σ represents the activation function, N represents the number of feature maps in the dynamic screening layer, and λ in represents the weight of the i-th program variable on the n-th feature map, x i represents the eigenvalue of the i-th program variable, α n represents the nonlinear factor, ω n represents the frequency parameter on the nth feature map, f k represents the kth program variable feature dimension, θ n represents the phase shift on the nth feature map, exp represents the exponential function, μ n represents the time decay rate, and t represents the time step; S23, in the auxiliary flow, the operating environment characteristics are analyzed based on dynamic environment modeling, and a multi-scale association between program variables and operating environment characteristics is established through environment labels and operating environment characteristic distribution; S24. Use the multi-head attention mechanism to analyze the weight changes of program variables under different operating environments and generate a dynamic weight distribution matrix: Among them, W d (i,j) represents the weight of the i-th program variable on the j-th environmental feature dimension, a ij Represents program variable z i and environmental characteristics j The static association score, ρ m (z i ,e j ) represents the mth head in the multi-head attention mechanism for the program variable z i and environmental characteristics j The weight, ρ m (z p ,e j ) represents the mth head in the multi-head attention mechanism for the program variable z p and environmental characteristics j The weight, γ m represents the amplitude adjustment factor of the mth head, a pj represents the weight of the p-th program variable on the j-th environment feature dimension, h represents the number of heads of the multi-head attention mechanism, M represents the total number of program variables, and z i represents the ith program variable, z p represents the pth program variable, e j represents the jth environmental feature; S25. Perform weighted fusion on the global importance score matrix generated by the mainstream and the dynamic weight distribution matrix generated by the auxiliary flow to calculate the optimized weight distribution matrix of the program variables: P o (i,k,j)=β1·ln(1+M s (i,k) 2 )+β2·W d (i,j); Among them, P o (i, k, j) represents the optimization weight of the i-th program variable in the k-th program variable feature dimension and the j-th environment feature dimension, and β1 and β2 represent the weight distribution coefficients S26. Output the optimized weight distribution matrix P of program variables o (i,k,j).

3. The method for simplifying program variables of an air-conditioning control panel based on deep learning according to claim 1, characterized in that: The S3 specifically includes: S31, construct a dynamic variant mechanism, the dynamic variant mechanism includes a dynamic perturbation module, a period adjustment module and a nonlinear weight optimization module, and uses the variant factor module to optimize the weight distribution matrix P of the program variables. o (i, k, j) performs dynamic nonlinear adjustment and calculates the optimized program variable weight matrix: Where Q(i,j) represents the optimization weight of the i-th program variable on the j-th environment feature dimension, K represents the total number of program variable feature dimensions, and η k Represents the weight adjustment coefficient for the kth program variable feature dimension in the variant factor module, ReLU represents the linear correction function, represents the perturbation factor of the kth program variable feature dimension, ω k represents the frequency parameter of the kth program variable feature dimension, θ k represents the phase shift of the kth program variable feature dimension, f k represents the kth program variable feature dimension, μ k Represents the decay rate of weight as the feature dimension changes, P o (i, k, j) represents the optimization weight of the i-th program variable in the k-th program variable feature dimension and the j-th environment feature dimension, and exp represents the exponential function; The dynamic perturbation module is used to adjust the feature dimension f of the kth program variable k Introduce the perturbation factor of the kth program variable feature dimension Used to simulate the randomness of environmental changes during weight adjustment; The periodic adjustment module uses the periodic adjustment function sin(ω k f k +θ k ) captures the periodic fluctuations of the characteristic dimensions of program variables; The nonlinear weight optimization module uses the linear correction function ReLU and the dynamic attenuation function exp(-μ k f k ) realizes nonlinear adjustment of weight values; S32, the dynamic variant mechanism dynamically extracts the program variable set by combining the optimized program variable weight matrix with the environmental characteristics: in, represents the characteristic value of the i-th program variable in the extracted program variable set, x i represents the initial characteristic value of the i-th program variable, and τ(j) represents the dynamic screening threshold of the j-th environmental feature dimension: Where M represents the total number of program variables, δ represents the dynamic screening sensitivity parameter, and Q mean Represents the mean of the optimized weights on the j-th environmental feature dimension.

4. The method for simplifying program variables of an air-conditioning control panel based on deep learning according to claim 1, characterized in that: The S4 specifically includes: S41, inputting the generated program variable set into a policy network based on an Actor-Critic structure, wherein the policy network includes an action generation module and a value evaluation module; S42, in the action generation module, generating corresponding actions according to the current state of the program variable set, wherein the actions include a decision of removing or retaining each program variable; S43, in the value evaluation module, the action generated by the action generation module is evaluated for value, and a comprehensive analysis is performed based on the state of the program variable set and the impact of the action on storage efficiency and program performance to generate a value evaluation result; S44, optimizing the policy network through a policy optimization algorithm based on the actions generated by the action generation module and the value evaluation results of the value evaluation module; S45, further screening the program variable set according to the optimized strategy network, removing unnecessary program variables, and retaining key program variables; S46. Finally, a filtered program variable set is generated.

5. The method for simplifying program variables of an air-conditioning control panel based on deep learning according to claim 1, characterized in that: The S5 specifically includes: S51, receiving the filtered program variable set, constructing an initial variable dependency graph with the program variables as nodes, wherein the edges of the initial variable dependency graph represent functional correlations between the program variables; S52. Calculate the weights of the edges in the initial variable dependency graph, and use a dynamic correlation analysis method to combine the mutual information of the variables and the call frequency to quantify the dependency weights: Among them, E(p,q) represents the program variable x p and the program variable x q The dependency weight between them, ζ represents the balance factor, I(x p ,x q ) represents the program variable x p and the program variable x q The mutual information value, F(x p ,x q ) represents the program variable x p and the program variable x q The number of joint calls of , T represents the total number of calls of the program variable; S53, generating a variable dependency topology graph according to the calculated dependency weights, wherein the edge weights in the variable dependency topology graph represent the functional correlation between program variables, and modeling the structural relationship between program variables from a global perspective; S54, based on the generated variable dependency topology graph, using an improved minimum spanning tree algorithm to prune redundant paths, wherein the improved minimum spanning tree algorithm includes: giving priority to edges with high weights during the calculation process to ensure that the core functional relationship between program variables is preserved; introducing a hierarchical screening mechanism to group dependency weights according to a dynamic range, and giving priority to pruning redundant paths in low-weight groups; and dynamically adjusting the pruning threshold in each iteration; S55. Optimize the variable dependency topology graph pruned by the improved minimum spanning tree algorithm to generate a final streamlined set of program variables.

6. The method for simplifying program variables of an air-conditioning control panel based on deep learning according to claim 1, characterized in that: The S6 specifically includes: S61, receiving the final streamlined program variable set, and mapping it to the control logic template, and automatically generating a new control logic program according to the functional dependency relationship and operation logic of the program variables; S62, inputting the new control logic program into an embedded simulation tool for simulation verification, where the simulation tool includes a storage efficiency module, an operation speed module, and a response delay module; S63, using the storage efficiency module to calculate the storage occupancy rate of the new control logic program, comparing the storage usage before and after the optimization, and recording the storage efficiency improvement ratio; S64, using the running speed module to measure the average execution time of the new control logic program under different workloads, and analyzing whether the processing performance of the program meets the running requirements of the air conditioning control board; S65, using the response delay module to measure the time interval from the input signal to the generation of the output control signal of the new control logic program, to verify whether the real-time performance of the program meets the expected performance indicators; S66. Deploy the new control logic program that has been verified by embedded simulation and meets the requirements of storage efficiency, operation speed and response delay to the air conditioning control board, and perform functional testing in the actual operating environment.

Images