A circuit board low power sleep mode switching method based on fuzzy logic

Abstract

The present invention discloses a circuit board low-power sleep mode switching method based on fuzzy logic, comprising the following steps: S1, collecting the core input parameters of the circuit board, using the information entropy flow control algorithm to perform energy modeling, and identifying the information entropy overload and low consumption points; S2, generating a fuzzy rule base based on the fuzzy logic control module; S3, introducing an entropy flow self-regulation mechanism, and automatically balancing the information entropy flow of each module through real-time monitoring; S4, generating a multi-level power consumption switching path based on real-time information entropy; S5, using information entropy feedback to automatically adjust the entropy flow rate; S6, optimizing the fuzzy rule base through a long-term memory mechanism to achieve accurate low-power consumption management; S7, predicting future power consumption changes and adjusting strategies in advance. The present invention effectively solves the problem of inaccurate power consumption mode switching in the prior art, improves the efficiency and stability of circuit board energy consumption management, and extends the battery life of the device.

Description

Technical Field

[0001] The present invention relates to the technical field of fuzzy logic, and in particular to a circuit board low-power sleep mode switching method based on fuzzy logic. Background Art

[0002] As the functions of modern electronic devices become more and more complex, power consumption management has gradually become one of the core technical challenges. Especially in the design and control of circuit boards, how to achieve smarter and more accurate low-power consumption management is an urgent problem that the current electronics industry needs to solve. Traditional power consumption management methods are mostly based on simple fixed threshold settings, or switching through certain predefined rules. However, with the improvement of circuit board integration and the complexity of the working environment, the limitations of these methods are becoming more and more obvious, which are specifically manifested in the following aspects.

[0003] Traditional power management systems usually use a static power switching mechanism, that is, when certain parameters (such as battery power, load status, etc.) reach a preset threshold, the system automatically switches to low power mode. However, this static switching mechanism fails to take into account the actual needs of the circuit board in different working environments. For example, when the load of the circuit board fluctuates greatly or the operating environment temperature changes drastically, a single threshold setting is difficult to accurately reflect the power consumption requirements of the system, which may cause the system to enter low power mode too early or too late, thereby affecting the performance and stability of the circuit board.

[0004] In a complex working environment, the power consumption requirements of the circuit board change frequently. The power consumption switching in the prior art is mostly adjusted based on preset power or voltage parameters. However, these simple rules are difficult to cope with real-time dynamic changes in energy consumption, especially when multiple modules work together, misjudgment of power consumption mode switching often occurs. The frequency of power consumption switching in the prior art may also cause system instability. Frequent switching of power consumption modes not only accelerates battery consumption, but also may cause the system to be unable to respond to external inputs in a timely manner, affecting the user experience.

[0005] Modern circuit boards often integrate multiple functional modules, and the power consumption of each module will affect each other. However, existing power management systems mostly control a single module and lack global control over the energy flow between modules. For example, some modules may consume more energy when working, while other modules consume less power, but the power management mechanism between these modules does not fully consider the energy transfer and mutual influence between multiple modules, which leads to unsatisfactory power optimization of the entire system.

[0006] Most existing power consumption management methods are post-adjustment, that is, the power consumption mode switch is triggered only when the system power consumption reaches a certain threshold. Due to the lack of the ability to predict energy consumption trends, many power consumption management systems cannot be adjusted in advance, which may cause the system to experience multiple power consumption mode switches in a short period of time, increasing energy consumption. The existing technology lacks a dynamic adaptive adjustment mechanism and cannot make intelligent adjustments based on the real-time status of the system and the historical power consumption change trend. This defect greatly limits the flexibility of the system in complex environments.

[0007] When switching modes, current power management systems rely more on direct energy parameters such as voltage and current, without in-depth consideration of the energy transfer and information entropy flow characteristics within the system. During the operation of the circuit board, the flow of information entropy between different modules directly affects the energy transfer and dissipation of the system, and the existing technology lacks comprehensive modeling and real-time monitoring of the flow of information entropy, which limits the effectiveness of the system in energy management. Failure to fully utilize the information entropy flow model to predict and adjust power consumption is a major shortcoming of existing power management technology.

[0008] As an intelligent control algorithm capable of processing uncertain information, fuzzy logic control has gradually attracted attention in the field of power consumption management in recent years. However, in existing power consumption management systems, the application of fuzzy logic is still in its infancy, mainly focusing on simple threshold judgment and control rule setting, and failing to give full play to the advantages of fuzzy logic in processing complex and multi-dimensional energy information. Especially in scenarios of multi-module collaboration and complex energy transfer, the application of fuzzy logic control is insufficient, resulting in a low level of intelligence in existing power consumption management systems. Therefore, how to provide a circuit board low-power sleep mode switching method based on fuzzy logic is an urgent problem that technicians in this field need to solve. Summary of the invention

[0009] One purpose of the present invention is to propose a circuit board low-power sleep mode switching method based on fuzzy logic. The present invention makes full use of the technology of combining fuzzy logic control with information entropy flow control, and describes in detail the algorithm for intelligently implementing the low-power mode switching of the circuit board under different working states. It has the advantages of high accuracy, fast response speed and significant energy consumption optimization, and effectively improves the circuit board's battery life and operation stability.

[0010] A circuit board low power sleep mode switching method based on fuzzy logic according to an embodiment of the present invention comprises the following steps:

[0011] S1. Collect the core input parameters of the circuit board, including battery power, load status, working time, use environment and signal noise, use the information entropy flow control algorithm to model the energy status of each module in the circuit board, and identify the information entropy overload and low consumption points;

[0012] S2, based on the fuzzy logic control module, a fuzzy rule base is generated in combination with the information entropy flow model;

[0013] S3, introduce the entropy flow self-regulation mechanism, by real-time monitoring the entropy flow changes of each module in the circuit board, automatically balance the information entropy flow between modules;

[0014] S4, generating a multi-level power consumption switching path by combining the fuzzy reasoning mechanism with the information entropy flow control, wherein the path is adjusted based on the real-time information entropy state of the circuit board module;

[0015] S5. Using the feedback result of the information entropy flow control algorithm, the entropy flow rate of each module is automatically adjusted when switching to the low power consumption mode;

[0016] S6. Through the long-term memory feedback mechanism, the fuzzy rule base is optimized in combination with the historical information entropy flow data, and accurate low-power management is achieved according to the entropy flow patterns of different modules;

[0017] S7. Based on the long-term change trend of information entropy flow, predict future power consumption switching and adjust the system's entropy flow management strategy in advance.

[0018] Optionally, the S1 includes the following steps:

[0019] S11, collect the core input parameters of the circuit board, and monitor the current power, load and the impact of the external environment on power consumption in real time;

[0020] S12, using multi-scale wavelet transform to perform denoising and decomposition processing on the collected signal;

[0021] S13. Use the information entropy flow algorithm to model the energy state of each module of the circuit board; by calculating the nonlinear information entropy, adjust the power consumption switching strategy in real time according to the change of the module energy state:

[0022] ;

[0023] in, For the Information entropy of the module; For modules In time In state probability; To adjust the parameters of nonlinear changes; is the correction item; is the total number of energy states;

[0024] S14. Build an information entropy flow model to monitor the information interaction between different modules in real time:

[0025] ;

[0026] in, is the flow rate of information entropy; For the Modules and The coupling coefficient between modules; For the The information entropy of each module; For the The number of other modules that a module is coupled to;

[0027] S15. Control the information entropy diffusion process between modules through the dynamic entropy diffusion equation, keep the energy transfer stable and controllable, and optimize the power consumption mode switching path:

[0028] ;

[0029] in, is the time variation of the information entropy flow rate, is the energy dissipation coefficient; is the coupling coefficient between modules; is the diffusion factor; For the The information entropy flow rate of each module; For the The information entropy flow rate of each module; For the The information entropy diffusion rate of each module;

[0030] S16. Optimize the information entropy flow path through the Lagrangian solution method so that the energy transfer remains on the optimal path when the power consumption mode is switched:

[0031] ;

[0032] in, is the Lagrangian function; is the potential energy function; is the coefficient of restitution; For in time arrive Integrate between

[0033] S17. According to the constructed information entropy flow model, identify the overload points and low consumption points of information entropy, and optimize the power consumption switching strategy.

[0034] Optionally, S2 includes the following steps:

[0035] S21. Calculate the real-time information entropy value of each module according to the information entropy flow model , information entropy value Used to reflect the current energy status of the circuit board module and provide basic data for subsequent fuzzy rule generation:

[0036] ;

[0037] in, For the The information entropy of each module; For modules In time In state The probability of To adjust the parameters of nonlinear changes; is the correction item; is the total number of energy states;

[0038] S22, based on information entropy value , generate the initial fuzzy membership function , which is used to describe the membership of the energy state of the circuit board module in the fuzzy logic system:

[0039] ;

[0040] in, For the Fuzzy membership of modules; Adjustment parameters to control the change of membership; is the center point of the fuzzy rule;

[0041] S23. Construct a preliminary fuzzy rule base based on membership function , rule base The reasoning formula of the fuzzy rule base used to deduce the energy state of each module during low-power switching is:

[0042] ;

[0043] in, It is a preliminary fuzzy rule; is the energy adjustment value; is the membership function;

[0044] S24. Based on the preliminary fuzzy rule base , the reasoning results of each module are input into the fuzzy reasoning system, and the reasoning system combines the power consumption mode and energy state of the current circuit board to generate a global fuzzy rule base , to cope with different operating states of the circuit board;

[0045] S25, the fuzzy reasoning system performs weighted aggregation on the energy states of each module;

[0046] S26, combining the historical energy state and the current information entropy flow trend, adjusting the rule weights of the global fuzzy rule base, and adaptively updating the fuzzy rule base according to real-time data;

[0047] S27, output the final fuzzy rule base , used for low-power mode switching decisions of the circuit board in different states.

[0048] Optionally, S3 includes the following steps:

[0049] S31, real-time monitoring of the information entropy flow of each module in the circuit board, and calculation of the Entropy flow rate of the module , looking for nonlinear coupling and time variation between modules, reflecting the complex energy flow state:

[0050] ;

[0051] in, For the The entropy flow rate of the module; For modules The rate at which the entropy of changes with time; For modules and The coupling coefficient between is the coupling change rate coefficient, which changes with time; is the coupling function of the entropy state, which is used to describe the nonlinear interaction between modules; is the total number of energy states; For the The information entropy of each module; For the The information entropy of each module; For in time arrive Integrate between

[0052] S32, based on entropy flow rate The energy transfer path between modules is adjusted based on the calculation results;

[0053] S33, balance the information entropy flow between modules and calculate the energy balance state between modules , introducing the quadratic nonlinearity of the coupled state:

[0054] ;

[0055] in, For the Energy balance status of the module; is the balance coefficient between modules; is a dynamic adjustment coefficient used to correct the change of high-order information entropy; For the Module information entropy flow rate; For the Module information entropy flow rate; For the The number of other modules that a module is coupled to; For the The information entropy of each module;

[0056] S34. Calculate the total energy flow rate of the system , by introducing the time integral term, the expression of energy flow is further optimized;

[0057] S35. Combine the energy flow state of the system to optimize the energy transfer path during low power switching. The formula is as follows:

[0058] ;

[0059] in, It is the optimal energy transfer path; is the entropy weight adjustment coefficient between modules; For the The derivative of the information entropy flow rate of each module; For the The information entropy of each module;

[0060] S36, according to the energy flow self-regulation mechanism, dynamically adjust the energy transfer path between modules and update the energy transfer coefficient of the modules in real time ;

[0061] S37, output the final energy transfer path , the energy transfer is optimized when switching power consumption modes through a dynamic balancing mechanism.

[0062] Optionally, S4 includes the following steps:

[0063] S41, real-time information entropy status of each module based on the circuit board , the fuzzy membership of each module is calculated through the fuzzy reasoning mechanism , determine whether the module enters low power mode;

[0064] S42. Based on the fuzzy reasoning results, use the information entropy flow algorithm to generate a preliminary power consumption switching path for each module ;

[0065] S43, through the multi-level reasoning mechanism, further optimize the power switching path, first, calculate the entropy flow rate of each module , reflects the information entropy transfer between modules;

[0066] S44, based on entropy flow rate , nonlinear adjustment of the power consumption switching path;

[0067] S45, combining the optimal power consumption switching paths of each module to generate a global power consumption switching path ;

[0068] S46, dynamically adjusting the parameters of the global power consumption switching path based on the real-time information entropy change trend of the system, and performing adaptive updating;

[0069] S47, switch path according to final power consumption , controls the power consumption state switching of the circuit board module to ensure stability and energy efficiency when switching to low power consumption mode.

[0070] Optionally, S5 includes the following steps:

[0071] S51. After completing the preliminary test, obtain the test results of each module ;in, For the The test results of the module; For the The real-time information entropy of the module; It is a detection function based on information entropy, used for recursive fusion calculation;

[0072] S52. Based on preliminary test results , use the recursive resonance fusion algorithm to iteratively fuse the detection results of multiple modules:

[0073] ;

[0074] in, is the global abnormal pattern after fusion; The weight of each module; is the adjustment coefficient of recursive fusion; For the Preliminary test results of the module; For the Preliminary test results of the module; To describe the The module's preliminary test results and The fusion function of the interaction of the preliminary detection results of the modules; is the total number of modules; For in time arrive Integrate between

[0075] S53. Continuously adjust the weight of each module through the recursive resonance mechanism , so that the fusion results gradually tend to be stable;

[0076] S54. Extracting global abnormal patterns through recursive resonance fusion algorithm , used to identify abnormal states of the circuit board in low-power mode;

[0077] S55, according to the global abnormal mode , correct the local detection results to avoid power consumption mode switching errors caused by local misjudgment;

[0078] S56. Based on the corrected detection results, the power consumption modes of all modules are uniformly adjusted to ensure global consistency in low power consumption mode switching;

[0079] S57, output the final test results , as a reference for switching the power consumption mode of the circuit board, and optimizing the consistency and accuracy of the global and local detection results.

[0080] Optionally, the S6 includes the following steps:

[0081] S61. According to the test results , using an adaptive feature feedback mechanism to evaluate the detection contribution of each module ;

[0082] S62. Based on the contribution of each module, update the weight coefficient of each module in the expert network , and adaptively adjust the weights so that the role of high-contribution modules in detection is enhanced and the weights of low-contribution modules are reduced;

[0083] S63, using the adaptive feedback mechanism, calculate the adaptive adjustment parameters of each module , used to correct the detection results of the module under the new abnormal mode;

[0084] S64, based on the module's adaptive adjustment parameters, dynamically adjust each module in the expert network structure to increase the ability to respond to new abnormal patterns;

[0085] S65. Globally optimize the entire expert network and fine-tune the parameters of all modules through the adaptive adjustment mechanism so that the network structure can adapt to new abnormal patterns;

[0086] S66. Optimize the feature feedback mechanism based on historical data of the detection results, and dynamically update the parameters of the feature feedback model;

[0087] S67. Based on the optimization results of the adaptive feature feedback mechanism, the structure and parameters of the expert network are comprehensively adjusted to ensure that it can cope with new abnormal patterns and achieve accurate detection.

[0088] The beneficial effects of the present invention are:

[0089] The present invention uses an information entropy flow control algorithm to monitor the energy transfer state of each module of the circuit board in real time and establish an energy model. The information entropy flow algorithm can capture the energy flow between modules in real time, and can dynamically adjust the power consumption switching mode of the system according to the energy dissipation and transfer state between different modules. The application of this algorithm enables the present invention to have the ability to handle complex energy flow situations, ensure that the system always maintains energy balance under different load conditions, and avoid the problem of energy waste or untimely switching caused by simple threshold setting in traditional power consumption switching methods.

[0090] The fuzzy logic control module adopted by the present invention further improves the flexibility of power consumption management through the generation and adaptive adjustment of the fuzzy rule base. Fuzzy logic generates an accurate power consumption adjustment rule base by analyzing multi-dimensional real-time parameters, including battery power, load status, ambient temperature, etc. The fuzzy rule base can flexibly adjust the system's low-power switching strategy according to the real-time working status of each module, thereby avoiding the misjudgment phenomenon of the traditional fixed threshold system due to external environmental changes or load fluctuations. The introduction of fuzzy logic significantly improves the system's ability to adapt to changes in the external environment and ensures the accuracy and flexibility of power consumption mode switching.

[0091] The present invention further improves the accuracy of multi-module collaborative work through a recursive resonance fusion algorithm. The recursive resonance fusion algorithm can effectively fuse the detection results of different modules and extract global abnormal patterns. Through recursive iteration, the algorithm can adaptively optimize the detection results of each module to ensure that in a complex working environment, the system will not generate unnecessary power switching due to local misjudgment. The introduction of the recursive resonance fusion algorithm not only improves the efficiency of the collaborative work of each module, but also improves the global detection accuracy of the system, greatly reducing the misjudgment rate of the system in low power consumption mode.

[0092] The application of the adaptive feature feedback mechanism enables the power consumption management system of the present invention to have higher self-learning and self-adjustment capabilities. The adaptive feature feedback mechanism continuously optimizes the structure and parameter settings of the expert network by monitoring the abnormal modes and energy consumption changes of the system in real time, ensuring that the system can quickly respond to new abnormal modes. The mechanism can dynamically adjust the parameters of the system according to real-time data, improve the system's ability to handle new power consumption requirements, and further enhance the long-term adaptability and scalability of the system through learning and feedback optimization of historical energy states.

[0093] Through the combination of multiple innovative algorithms, the low-power mode switching method of the present invention significantly improves the energy management efficiency of the system in complex environments, and solves the problems of inaccurate power switching, insufficient module coordination, and high misjudgment rate in the prior art. At the same time, the present invention achieves more efficient power consumption control and longer device battery life by dynamically adjusting the system's power consumption mode, optimizing the energy transfer path, and adaptively adjusting module parameters. BRIEF DESCRIPTION OF THE DRAWINGS

[0094] 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:

[0095] Figure 1 A flowchart of a circuit board low power sleep mode switching method based on fuzzy logic proposed by the present invention;

[0096] Figure 2 A schematic diagram of an energy flow monitoring module of the information entropy flow control algorithm proposed in the present invention;

[0097] Figure 3 This is a flow chart of fusing multi-module detection results using the recursive resonance fusion algorithm proposed in the present invention. DETAILED DESCRIPTION

[0098] 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.

[0099] refer to Figure 1-3 , a circuit board low power sleep mode switching method based on fuzzy logic, comprising the following steps:

[0100] S1. Collect the core input parameters of the circuit board, including battery power, load status, working time, use environment and signal noise, use the information entropy flow control algorithm to model the energy status of each module in the circuit board, and identify the information entropy overload and low consumption points;

[0101] S2, based on the fuzzy logic control module, a fuzzy rule base is generated in combination with the information entropy flow model;

[0102] S3, introduce the entropy flow self-regulation mechanism, by real-time monitoring the entropy flow changes of each module in the circuit board, automatically balance the information entropy flow between modules;

[0103] S4, generating a multi-level power consumption switching path by combining the fuzzy reasoning mechanism with the information entropy flow control, wherein the path is adjusted based on the real-time information entropy state of the circuit board module;

[0104] S5. Using the feedback result of the information entropy flow control algorithm, the entropy flow rate of each module is automatically adjusted when switching to the low power consumption mode;

[0105] S6. Through the long-term memory feedback mechanism, the fuzzy rule base is optimized in combination with the historical information entropy flow data, and accurate low-power management is achieved according to the entropy flow patterns of different modules;

[0106] S7. Based on the long-term change trend of information entropy flow, predict future power consumption switching and adjust the system's entropy flow management strategy in advance.

[0107] In this implementation, S1 includes the following steps:

[0108] S11, collect the core input parameters of the circuit board, and monitor the current power, load and the impact of the external environment on power consumption in real time;

[0109] S12, using multi-scale wavelet transform to perform denoising and decomposition processing on the collected signal;

[0110] S13. Use the information entropy flow algorithm to model the energy state of each module of the circuit board; by calculating the nonlinear information entropy, adjust the power consumption switching strategy in real time according to the change of the module energy state:

[0111] ;

[0112] in, For the Information entropy of the module; For modules In time In state The probability of To adjust the parameters of nonlinear changes; is the correction item; is the total number of energy states;

[0113] S14. Build an information entropy flow model to monitor the information interaction between different modules in real time:

[0114] ;

[0115] in, is the flow rate of information entropy; For the Modules and The coupling coefficient between modules; For the The information entropy of each module; For the The number of other modules that a module is coupled to;

[0116] S15. Control the information entropy diffusion process between modules through the dynamic entropy diffusion equation, keep the energy transfer stable and controllable, and optimize the power consumption mode switching path:

[0117] ;

[0118] in, is the time variation of the information entropy flow rate, is the energy dissipation coefficient; is the coupling coefficient between modules; is the diffusion factor; For the The information entropy flow rate of each module; For the The information entropy flow rate of each module; For the The information entropy diffusion rate of each module;

[0119] S16. Optimize the information entropy flow path through the Lagrangian solution method so that the energy transfer remains on the optimal path when the power consumption mode is switched:

[0120] ;

[0121] in, is the Lagrangian function; is the potential energy function; is the coefficient of restitution; For in time arrive Integrate between

[0122] S17. According to the constructed information entropy flow model, identify the overload points and low consumption points of information entropy, and optimize the power consumption switching strategy.

[0123] In this implementation, S2 includes the following steps:

[0124] S21. Calculate the real-time information entropy value of each module according to the information entropy flow model , information entropy value Used to reflect the current energy status of the circuit board module and provide basic data for subsequent fuzzy rule generation:

[0125] ;

[0126] in, For the The information entropy of each module; For modules In time In state The probability of To adjust the parameters of nonlinear changes; is the correction item; is the total number of energy states;

[0127] S22, based on information entropy value , generate the initial fuzzy membership function , which is used to describe the membership of the energy state of the circuit board module in the fuzzy logic system:

[0128] ;

[0129] in, For the Fuzzy membership of modules; To control the adjustment parameters of membership changes; is the center point of the fuzzy rule;

[0130] S23. Construct a preliminary fuzzy rule base based on membership function , rule base The reasoning formula of the fuzzy rule base used to deduce the energy state of each module during low-power switching is:

[0131] ;

[0132] in, It is a preliminary fuzzy rule; is the energy adjustment value; is the membership function;

[0133] S24. Based on the preliminary fuzzy rule base , the reasoning results of each module are input into the fuzzy reasoning system, and the reasoning system combines the power consumption mode and energy state of the current circuit board to generate a global fuzzy rule base , to cope with different operating states of the circuit board;

[0134] S25, the fuzzy reasoning system performs weighted aggregation on the energy states of each module;

[0135] S26, combining the historical energy state and the current information entropy flow trend, adjusting the rule weights of the global fuzzy rule base, and adaptively updating the fuzzy rule base according to real-time data;

[0136] S27, output the final fuzzy rule base , used for low-power mode switching decisions of the circuit board in different states.

[0137] In this implementation, S3 includes the following steps:

[0138] S31, real-time monitoring of the information entropy flow of each module in the circuit board, and calculation of the Entropy flow rate of the module , looking for nonlinear coupling and time variation between modules, reflecting the complex energy flow state:

[0139] ;

[0140] in, For the The entropy flow rate of the module; For modules The rate at which the entropy of changes with time; For modules and The coupling coefficient between is the coupling change rate coefficient, which changes with time; is the coupling function of the entropy state, which is used to describe the nonlinear interaction between modules; is the total number of energy states; For the The information entropy of each module; For the The information entropy of each module; For in time arrive Integrate between

[0141] S32, based on entropy flow rate The energy transfer path between modules is adjusted based on the calculation results;

[0142] S33, balance the information entropy flow between modules and calculate the energy balance state between modules , introducing the quadratic nonlinearity of the coupled state:

[0143] ;

[0144] in, For the Energy balance status of the module; is the balance coefficient between modules; is a dynamic adjustment coefficient used to correct the change of high-order information entropy; For the Module information entropy flow rate; For the Module information entropy flow rate; For the The number of other modules that a module is coupled to; For the The information entropy of each module;

[0145] S34. Calculate the total energy flow rate of the system , by introducing the time integral term, the expression of energy flow is further optimized;

[0146] S35. Combine the energy flow state of the system to optimize the energy transfer path during low power switching. The formula is as follows:

[0147] ;

[0148] in, It is the optimal energy transfer path; is the entropy weight adjustment coefficient between modules; For the The derivative of the information entropy flow rate of each module; For the The information entropy of each module;

[0149] S36, according to the energy flow self-regulation mechanism, dynamically adjust the energy transfer path between modules and update the energy transfer coefficient of the modules in real time ;

[0150] S37, output the final energy transfer path , the energy transfer is optimized when switching power consumption modes through a dynamic balancing mechanism.

[0151] In this implementation, S4 includes the following steps:

[0152] S41, real-time information entropy status of each module based on the circuit board , the fuzzy membership of each module is calculated through the fuzzy reasoning mechanism , determine whether the module enters low power mode;

[0153] S42. Based on the fuzzy reasoning results, use the information entropy flow algorithm to generate a preliminary power consumption switching path for each module ;

[0154] S43, through the multi-level reasoning mechanism, further optimize the power switching path, first, calculate the entropy flow rate of each module , reflects the information entropy transfer between modules;

[0155] S44, based on entropy flow rate , nonlinear adjustment of the power consumption switching path;

[0156] S45, combining the optimal power consumption switching paths of each module to generate a global power consumption switching path ;

[0157] S46, dynamically adjusting the parameters of the global power consumption switching path based on the real-time information entropy change trend of the system, and performing adaptive updating;

[0158] S47, switch path according to final power consumption , controls the power consumption state switching of the circuit board module to ensure stability and energy efficiency when switching to low power consumption mode.

[0159] In this implementation, S5 includes the following steps:

[0160] S51. After completing the preliminary test, obtain the test results of each module ;in, For the The test results of the module; For the The real-time information entropy of the module; It is a detection function based on information entropy, used for recursive fusion calculation;

[0161] S52. Based on preliminary test results , use the recursive resonance fusion algorithm to iteratively fuse the detection results of multiple modules:

[0162] ;

[0163] in, is the global abnormal pattern after fusion; The weight of each module; is the adjustment coefficient of recursive fusion; For the Preliminary test results of the module; For the Preliminary test results of the module; To describe the The module's preliminary test results and The fusion function of the interaction of the preliminary detection results of the modules; is the total number of modules; For in time arrive Integrate between

[0164] S53. Continuously adjust the weight of each module through the recursive resonance mechanism , so that the fusion results gradually tend to be stable;

[0165] S54. Extracting global abnormal patterns through recursive resonance fusion algorithm , used to identify abnormal states of the circuit board in low-power mode;

[0166] S55, according to the global abnormal mode , correct the local detection results to avoid power consumption mode switching errors caused by local misjudgment;

[0167] S56. Based on the corrected detection results, the power consumption modes of all modules are uniformly adjusted to ensure global consistency in low power consumption mode switching;

[0168] S57, output the final test results , as a reference for switching the power consumption mode of the circuit board, and optimizing the consistency and accuracy of the global and local detection results.

[0169] In this implementation, S6 includes the following steps:

[0170] S61. According to the test results , using an adaptive feature feedback mechanism to evaluate the detection contribution of each module ;

[0171] S62. Based on the contribution of each module, update the weight coefficient of each module in the expert network , and adaptively adjust the weights so that the role of high-contribution modules in detection is enhanced and the weights of low-contribution modules are reduced;

[0172] S63, using the adaptive feedback mechanism, calculate the adaptive adjustment parameters of each module , used to correct the detection results of the module under the new abnormal mode;

[0173] S64, based on the module's adaptive adjustment parameters, dynamically adjust each module in the expert network structure to increase the ability to respond to new abnormal patterns;

[0174] S65. Globally optimize the entire expert network and fine-tune the parameters of all modules through the adaptive adjustment mechanism so that the network structure can adapt to new abnormal patterns;

[0175] S66. Optimize the feature feedback mechanism based on historical data of the detection results, and dynamically update the parameters of the feature feedback model;

[0176] S67. Based on the optimization results of the adaptive feature feedback mechanism, the structure and parameters of the expert network are comprehensively adjusted to ensure that it can cope with new abnormal patterns and achieve accurate detection.

[0177] Embodiment 1:

[0178] In practical applications, smart home devices need to be in standby mode for a long time and respond to various commands at any time according to user needs. In standby mode, the power consumption of the device needs to be kept at an extremely low level to extend the battery life of the device. However, when the user wakes up the device or the environment changes significantly (such as a sudden increase in temperature or increased external signal interference), the device must quickly return to working mode. Traditional power management methods control power switching based on fixed thresholds, but the disadvantage of this method is that it cannot cope with complex and changing external environments, often resulting in delayed or frequent power switching, which increases energy consumption and affects the response speed of the device.

[0179] In the low-power management process of the smart home device, the system first collects key input parameters such as battery power, working time, temperature, signal noise, etc. of the device through sensors, and uses the information entropy flow control algorithm in the present invention to model the energy state of each module. Through the information entropy flow model, the system can monitor the energy transfer state of each module in real time, and accurately identify the information entropy overload points and low consumption points of the circuit board under different working modes. When the device is in standby mode, the fuzzy logic control module dynamically adjusts the timing of the system entering the low-power mode by generating a fuzzy rule base and combining the actual operating status of the device. In particular, when the environment changes, the system can quickly make adjustments based on the real-time energy dissipation situation to avoid frequent switching or excessive power consumption.

[0180] Once the device is awakened, the recursive resonance fusion algorithm will fuse the detection results of multiple modules and extract global abnormal patterns to avoid misjudgment of a single module, thereby ensuring that the device can stably and quickly enter the working mode and respond to user operations in a timely manner. After the device has been running for a long time, the adaptive feature feedback mechanism will adjust the expert network structure based on historical data, optimize the weights of each module, and further improve the system's power consumption management capabilities in complex working environments.

[0181] To verify the beneficial effects of the present invention, we conducted a 30-day field test in the laboratory. The test location was a laboratory for smart home devices, with a temperature range of 10°C to 30°C and a humidity range of 30% to 80%. The system was configured to be tested under a number of different workloads and environmental changes, including:

[0182] Normal working mode (users frequently wake up the device and data processing tasks are heavy);

[0183] Standby mode (the device enters a low-power mode);

[0184] Unusual environmental patterns (external temperature changes, increased signal interference, etc.).

[0185] A large amount of data was collected in each mode, and the power consumption management of the system was analyzed through the information entropy flow control algorithm, fuzzy logic control module, recursive resonance fusion algorithm and adaptive feature feedback mechanism. The following is some experimental data:

[0186] Table 1 Data table

[0187]

[0188] During the experiment, the low-power mode switching response time of the device was significantly shortened, by an average of 30%, and the device misjudgment rate was reduced by about 80%. In addition, the information entropy flow control algorithm combined with fuzzy logic control makes the system's power mode adjustment in different environments more flexible and accurate. For example, in abnormal environment mode, the system can quickly identify external interference and optimize the power switching strategy, thereby effectively avoiding the limitations of traditional threshold settings.

[0189] In the experimental data, in normal working mode, the power switching response time of the device is 145 milliseconds on average, and the misjudgment rate is maintained at about 2%, showing the system's efficient response to different energy states. In standby mode, battery power consumption is significantly reduced, and the power switching response time is also shortened to about 100 milliseconds, showing the advantages of low power management. In abnormal environment mode, although the ambient temperature and humidity change greatly, the system can still adapt quickly, the response time is kept within 180 milliseconds, and the misjudgment rate is also controlled below 3%, indicating the accuracy of the recursive resonance fusion algorithm in global detection.

[0190] 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 circuit board low power sleep mode switching method based on fuzzy logic, characterized in that: The steps include: S1. Collect the core input parameters of the circuit board, including battery power, load status, working time, use environment and signal noise, use the information entropy flow control algorithm to model the energy status of each module in the circuit board, and identify the information entropy overload and low consumption points; S2, based on the fuzzy logic control module, a fuzzy rule base is generated in combination with the information entropy flow model; S3, introduce the entropy flow self-regulation mechanism, by real-time monitoring the entropy flow changes of each module in the circuit board, automatically balance the information entropy flow between modules; S4, generating a multi-level power consumption switching path by combining the fuzzy reasoning mechanism with the information entropy flow control, wherein the path is adjusted based on the real-time information entropy state of the circuit board module; S5. Using the feedback result of the information entropy flow control algorithm, the entropy flow rate of each module is automatically adjusted when switching to the low power consumption mode; S6. Through the long-term memory feedback mechanism, the fuzzy rule base is optimized in combination with the historical information entropy flow data, and accurate low-power management is achieved according to the entropy flow patterns of different modules; S7. Based on the long-term change trend of information entropy flow, predict future power consumption switching and adjust the system's entropy flow management strategy in advance.

2. A circuit board low power sleep mode switching method based on fuzzy logic according to claim 1, characterized in that: The S1 comprises the following steps: S11, collect the core input parameters of the circuit board, and monitor the current power, load and the impact of the external environment on power consumption in real time; S12, using multi-scale wavelet transform to perform denoising and decomposition processing on the collected signal; S13. Use the information entropy flow algorithm to model the energy state of each module of the circuit board; by calculating the nonlinear information entropy, adjust the power consumption switching strategy in real time according to the change of the module energy state: ； in, For the Information entropy of the module; For modules In time In state probability; To adjust the parameters of nonlinear changes; is the correction item; is the total number of energy states; S14. Build an information entropy flow model to monitor the information interaction between different modules in real time: ； in, is the flow rate of information entropy; For the Modules and The coupling coefficient between modules; For the The information entropy of each module; For the The number of other modules that a module is coupled to; S15. Control the information entropy diffusion process between modules through the dynamic entropy diffusion equation, keep the energy transfer stable and controllable, and optimize the power consumption mode switching path: ； in, is the time variation of the information entropy flow rate, is the energy dissipation coefficient; is the coupling coefficient between modules; is the diffusion factor; For the The information entropy flow rate of each module; For the The information entropy flow rate of each module; For the The information entropy diffusion rate of each module; S16. Optimize the information entropy flow path through the Lagrangian solution method so that the energy transfer remains on the optimal path when the power consumption mode is switched: ； in, is the Lagrangian function; is the potential energy function; is the coefficient of restitution; For in time arrive Integrate between S17. According to the constructed information entropy flow model, identify the overload points and low consumption points of information entropy, and optimize the power consumption switching strategy.

3. The circuit board low power sleep mode switching method based on fuzzy logic according to claim 1, characterized in that: The S2 comprises the following steps: S21. Calculate the real-time information entropy value of each module according to the information entropy flow model , information entropy value Used to reflect the current energy status of the circuit board module and provide basic data for subsequent fuzzy rule generation: ； in, For the The information entropy of each module; For modules In time In state The probability of To adjust the parameters of nonlinear changes; is the correction item; is the total number of energy states; S22, based on information entropy value , generate the initial fuzzy membership function , which is used to describe the membership of the energy state of the circuit board module in the fuzzy logic system: ； in, For the Fuzzy membership of modules; To control the adjustment parameters of membership changes; is the center point of the fuzzy rule; S23. Construct a preliminary fuzzy rule base based on membership function , rule base The reasoning formula of the fuzzy rule base used to deduce the energy state of each module during low-power switching is: ； in, It is a preliminary fuzzy rule; is the energy adjustment value; is the membership function; S24. Based on the preliminary fuzzy rule base , the reasoning results of each module are input into the fuzzy reasoning system, and the reasoning system combines the power consumption mode and energy state of the current circuit board to generate a global fuzzy rule base , to cope with different operating states of the circuit board; S25, the fuzzy reasoning system performs weighted aggregation on the energy states of each module; S26, combining the historical energy state and the current information entropy flow trend, adjusting the rule weights of the global fuzzy rule base, and adaptively updating the fuzzy rule base according to real-time data; S27, output the final fuzzy rule base , used for low-power mode switching decisions of the circuit board in different states.

4. The circuit board low power sleep mode switching method based on fuzzy logic according to claim 1, characterized in that: The S3 comprises the following steps: S31, real-time monitoring of the information entropy flow of each module in the circuit board, and calculation of the Entropy flow rate of the module , looking for nonlinear coupling and time variation between modules, reflecting the complex energy flow state: ； in, For the The entropy flow rate of the module; For modules The rate at which the entropy of changes with time; For modules and The coupling coefficient between is the coupling change rate coefficient, which changes with time; is the coupling function of the entropy state, which is used to describe the nonlinear interaction between modules; is the total number of energy states; For the The information entropy of each module; For the The information entropy of each module; For in time arrive Integrate between S32, based on entropy flow rate The energy transfer path between modules is adjusted based on the calculation results; S33, balance the information entropy flow between modules and calculate the energy balance state between modules , introducing the quadratic nonlinearity of the coupled state: ； in, For the Energy balance status of the module; is the balance coefficient between modules; is a dynamic adjustment coefficient used to correct the change of high-order information entropy; For the Module information entropy flow rate; For the Module information entropy flow rate; For the The number of other modules that a module is coupled to; For the The information entropy of each module; S34. Calculate the total energy flow rate of the system , by introducing the time integral term, the expression of energy flow is further optimized; S35. Combine the energy flow state of the system to optimize the energy transfer path during low power switching. The formula is as follows: ； in, It is the optimal energy transfer path; is the entropy weight adjustment coefficient between modules; For the The derivative of the information entropy flow rate of each module; For the The information entropy of each module; S36, according to the energy flow self-regulation mechanism, dynamically adjust the energy transfer path between modules and update the energy transfer coefficient of the modules in real time ; S37, output the final energy transfer path , the energy transfer is optimized when switching power consumption modes through a dynamic balancing mechanism.

5. The circuit board low power sleep mode switching method based on fuzzy logic according to claim 1, characterized in that: The S4 comprises the following steps: S41, real-time information entropy status of each module based on the circuit board , the fuzzy membership of each module is calculated through the fuzzy reasoning mechanism , determine whether the module enters low power mode; S42. Based on the fuzzy reasoning results, use the information entropy flow algorithm to generate a preliminary power consumption switching path for each module ; S43, through the multi-level reasoning mechanism, further optimize the power switching path, first, calculate the entropy flow rate of each module , reflects the information entropy transfer between modules; S44, based on entropy flow rate , nonlinear adjustment of the power consumption switching path; S45, combining the optimal power consumption switching paths of each module to generate a global power consumption switching path ; S46, dynamically adjusting the parameters of the global power consumption switching path based on the real-time information entropy change trend of the system, and performing adaptive updating; S47, switch path according to final power consumption , controls the power consumption state switching of the circuit board module to ensure stability and energy efficiency when switching to low power consumption mode.

6. The circuit board low power sleep mode switching method based on fuzzy logic according to claim 1, characterized in that: The S5 comprises the following steps: S51. After completing the preliminary test, obtain the test results of each module ;in, For the The test results of the module; For the The real-time information entropy of the module; It is a detection function based on information entropy, used for recursive fusion calculation; S52. Based on preliminary test results , use the recursive resonance fusion algorithm to iteratively fuse the detection results of multiple modules: ； in, is the global abnormal pattern after fusion; The weight of each module; is the adjustment coefficient of recursive fusion; For the Preliminary test results of the module; For the Preliminary test results of the module; To describe the The module's preliminary test results and The fusion function of the interaction of the preliminary detection results of the modules; is the total number of modules; For in time arrive Integrate between S53. Continuously adjust the weight of each module through the recursive resonance mechanism , so that the fusion results gradually tend to be stable; S54. Extracting global abnormal patterns through recursive resonance fusion algorithm , used to identify abnormal states of the circuit board in low-power mode; S55, according to the global abnormal mode , correct the local detection results to avoid power consumption mode switching errors caused by local misjudgment; S56. Based on the corrected detection results, the power consumption modes of all modules are uniformly adjusted to ensure global consistency in low power consumption mode switching; S57, output the final test results , as a reference for switching the power consumption mode of the circuit board, and optimizing the consistency and accuracy of the global and local detection results.

7. The circuit board low power sleep mode switching method based on fuzzy logic according to claim 1, characterized in that: The S6 comprises the following steps: S61. According to the test results , using an adaptive feature feedback mechanism to evaluate the detection contribution of each module ; S62. Based on the contribution of each module, update the weight coefficient of each module in the expert network , and adaptively adjust the weights so that the role of high-contribution modules in detection is enhanced and the weights of low-contribution modules are reduced; S63, using the adaptive feedback mechanism, calculate the adaptive adjustment parameters of each module , used to correct the detection results of the module under the new abnormal mode; S64, based on the module's adaptive adjustment parameters, dynamically adjust each module in the expert network structure to increase the ability to respond to new abnormal patterns; S65. Globally optimize the entire expert network and fine-tune the parameters of all modules through the adaptive adjustment mechanism so that the network structure can adapt to new abnormal patterns; S66. Optimize the feature feedback mechanism based on historical data of the detection results, and dynamically update the parameters of the feature feedback model; S67. Based on the optimization results of the adaptive feature feedback mechanism, the structure and parameters of the expert network are comprehensively adjusted to ensure that it can cope with new abnormal patterns and achieve accurate detection.

Images