Exhibition hall intelligent control system and method based on Internet of Things technology

Abstract

The invention discloses an exhibition hall intelligent control system and method based on the Internet of Things technology, and the method comprises the following steps: collecting environment data in an exhibition hall in real time through a self-adaptive multi-mode sensor network, and dynamically adjusting the sampling frequency of a sensor through a multi-dimensional data sudden change monitoring algorithm by the system, the central processing module is combined with historical and real-time data, time sequence multi-dimensional regression analysis is adopted, an environment change prediction model is generated, then equipment control parameters are generated, the system dynamically adjusts the operation states of temperature equipment, illumination equipment and the like in the exhibition hall according to behavior data of visitors and the environment parameters, the experience of the visitors is optimized, and the experience of the visitors is improved. The intelligent anomaly detection module monitors the operation state of equipment in real time and identifies and isolates fault equipment in time, and the system preferentially guarantees equipment operation and reduces energy consumption when visitors are dense through a long-term energy consumption optimization learning algorithm, so that energy-saving management and long-term self-optimization of the exhibition hall are realized.

Description

Technical Field

[0001] The present invention relates to the field of intelligent exhibition hall control technology, and in particular to an exhibition hall intelligent control system and method based on Internet of Things technology. Background Art

[0002] Although the existing exhibition hall management and control systems can achieve a certain degree of environmental monitoring and equipment management, they still have many defects when facing complex and changeable environmental conditions and ever-changing visitor behaviors. Most existing exhibition hall systems rely on a single sensor network to monitor parameters such as temperature, humidity, and light, and control equipment operation through preset fixed algorithms. The main problem with this approach is that the system lacks the ability to respond to environmental changes in real time and dynamically. For example, when the environmental conditions inside and outside the exhibition hall suddenly change, or a large number of visitors flock to a certain exhibition area, it is difficult for traditional systems to respond to these changes in a timely manner, resulting in a delayed system response and an inability to quickly adjust equipment to maintain environmental stability and a comfortable experience for visitors. When dealing with equipment failures or abnormal conditions, existing systems often use preset fixed threshold judgment methods and lack intelligent detection and adaptive adjustment mechanisms. As exhibition hall operations become more complicated, single threshold detection often leads to equipment malfunctions or delayed repairs, affecting the overall stability of the system.

[0003] In terms of data processing, existing systems usually rely on data sources from a single or a few sensors, making it difficult to achieve fusion analysis of multi-source data. The environmental status in the exhibition hall is often determined by multi-dimensional parameters. Traditional systems usually only regulate based on a single parameter, while ignoring the synergy of other related parameters. This single data source model cannot fully and accurately reflect the actual environmental conditions of the exhibition hall, resulting in insufficient accuracy of environmental control; for example, when the density of people in the exhibition hall increases, adjusting the air-conditioning system only through temperature sensors may ignore the effects of lighting intensity and air circulation, ultimately leading to a decrease in comfort in local areas, while also increasing energy waste. Therefore, the existing system cannot perform efficient energy management and intelligent control under complex and changeable environmental conditions, and cannot meet the needs of modern smart exhibition halls for precise environmental regulation and energy-saving optimization.

[0004] Existing exhibition hall management systems have great limitations in fault detection and isolation. Traditional systems mostly use static fault detection mechanisms, and use preset parameter thresholds to determine whether the operating status of the equipment is abnormal. This static threshold method cannot cope with complex environments and equipment operating conditions, especially when environmental parameters and equipment loads change dynamically. The static detection mechanism often lags behind and cannot identify potential faults or hidden dangers in a timely manner. For example, when the air-conditioning equipment in the exhibition hall gradually fails, the traditional system may have to wait until the temperature exceeds the preset range before issuing an alarm, which often causes discomfort to visitors. When equipment failure occurs, traditional systems usually shut down the entire system or simply restart it. The lack of intelligent fault isolation and emergency handling capabilities leads to poor system stability, which further affects the operating efficiency of the exhibition hall.

[0005] Therefore, how to provide an exhibition hall intelligent control system and method based on Internet of Things technology is a problem that technical personnel in this field urgently need to solve. Summary of the invention

[0006] One purpose of the present invention is to propose an exhibition hall intelligent control system and method based on Internet of Things technology. The present invention realizes real-time dynamic monitoring and regulation of the exhibition hall environment through an adaptive multimodal sensor network, an intelligent anomaly detection and fault isolation module, a multi-source data fusion algorithm and an adaptive learning module; the present invention describes in detail how to use multi-dimensional data mutation monitoring technology, time series multi-dimensional regression analysis algorithm and long-term energy consumption optimization learning algorithm to accurately control environmental parameters such as temperature, humidity, light, noise in the exhibition hall, and dynamically adjust the working mode of the equipment according to the visitor behavior and the equipment operation status, which has the advantages of efficient energy consumption management, environmental self-optimization and high equipment operation safety.

[0007] According to an embodiment of the present invention, an exhibition hall intelligent control system and method based on Internet of Things technology includes the following steps: S1. Collect environmental data in the exhibition hall through an adaptive multimodal sensor network. The environmental data includes temperature, humidity, light intensity, noise, air quality and personnel flow data. The sensor network dynamically adjusts the sampling frequency and priority of the sensor through a multi-dimensional data mutation monitoring algorithm; S2. The collected environmental data is transmitted to the central processing module through the Internet of Things node. The central processing module combines the historical operation data with the real-time collected data and uses the improved time series multidimensional regression analysis algorithm to build an environmental change prediction model. The algorithm analyzes the time series data of temperature and humidity, personnel flow and equipment operation status, combines nonlinear multidimensional regression analysis, dynamically calculates the environmental change trend, and generates real-time equipment control parameters; S3, using the generated real-time device control parameters, and processing the multi-dimensional environmental data obtained by different sensors in real time through a multi-source data fusion algorithm to generate comprehensive environmental parameters; S4. Based on comprehensive environmental parameters and visitor behavior perception modules, the movement trajectory, residence time and density information of visitors are monitored in real time. The system dynamically adjusts the temperature and lighting parameters of relevant areas in the exhibition hall according to the visitor behavior data and comprehensive environmental parameters to optimize the personalized environmental experience of visitors; S5. When the system detects abnormalities in the monitored environmental parameters and equipment operating status, it uses the intelligent anomaly detection and fault isolation module to analyze the abnormal data, identify and isolate the source of the fault. The system adjusts the operating mode of other equipment based on the abnormal analysis results to maintain the overall environmental stability of the exhibition hall and the safety of the equipment; S6. Based on the abnormal analysis results and the current energy consumption status of the system, combined with the equipment control parameters and comprehensive environmental parameters, the system dynamically adjusts the power output of each device in the exhibition hall through a long-term energy consumption optimization learning algorithm. The system gives priority to ensuring the normal operation of the equipment when the number of visitors is dense, and reduces the power consumption of the equipment when the number of visitors decreases, thus realizing the energy efficiency management and energy saving optimization of the exhibition hall; S7. Through the feedback optimization mechanism, the system dynamically adjusts the equipment's operating strategy based on historical operating data, behavioral data and abnormal data, and combines long-term and short-term environmental change patterns with equipment status feedback to achieve long-term self-optimization of the exhibition hall environment.

[0008] Optionally, the S1 specifically includes: S11, configuring an adaptive multimodal sensor network, wherein the sensors include a temperature sensor T, a humidity sensor H, a light sensor L, a noise sensor N, an air quality sensor A, and a personnel flow sensor P, which are respectively arranged in multiple key areas of the exhibition hall to collect environmental data in real time according to the fluctuation characteristics of different environmental parameters in the exhibition hall; S12, set the initial sampling frequency of each sensor , , , , and ,in , , , , and The sampling frequencies for temperature, humidity, light, noise, air quality and personnel flow are respectively set at once per minute, and can be adaptively adjusted based on real-time fluctuation data through the central control module; S13, by analyzing the real-time collected environmental data, combined with the multi-dimensional mutation detection algorithm, dynamically calculate the sampling priority and , , , , and : ; in, is the change of environmental parameter X, is the weight factor, To adjust the constant, is the sampling priority of sensor X; S14, when the priority When the preset threshold is reached, the central processing module automatically and dynamically adjusts the sampling frequency of the corresponding sensor through the adaptive sampling adjustment mechanism : ; in, is the current sampling frequency, is the adjusted sampling frequency, is the sensitivity coefficient, k is the adjustment rate, is the change threshold; S15, according to the adjusted sampling frequency ,The sensor network continuously collects and transmits environmental data, which are transmitted to the central processing module through the Internet of Things nodes to generate the exhibition hall environment data set D.

[0009] Optionally, the S2 specifically includes: S21, transmitting the environmental data set D to the central processing module through the Internet of Things node, and generating a joint data set D' in combination with the historical operation data, wherein the joint data set D' includes all real-time and historical environmental data in the exhibition hall; S23, the central processing module uses the improved time series multidimensional regression analysis algorithm to build an environmental change prediction model based on the joint data set D', and analyzes the change trend of environmental parameters by combining time series data and nonlinear regression: ; in, To predict the environmental change value at the future time t+1, is the regression coefficient, is the environmental data at time t, is the nonlinear regression function, is the time correlation coefficient, is the nonlinear characteristic function describing time variation, is the error term; S24. In the environmental change prediction model, the input data includes temperature and humidity data T, H, personnel flow data P and equipment operation status , by analyzing the time correlation of each parameter, a real-time prediction model is generated: ; in, is the predicted temperature at the next moment, is the temperature change at time t, are the weights of different parameters, is a nonlinear function; S25. Based on the predicted environmental change value, the central processing module generates the equipment control parameter C. The control parameter comprehensively considers temperature, humidity, personnel flow and equipment operation status through the optimization formula: ; Among them, C is the device control parameter, is the weight coefficient of each environmental parameter, is a nonlinear function that describes environmental changes.

[0010] Optionally, the S4 specifically includes: S41. Monitor the movement trajectory of visitors in real time through the visitor behavior perception module , Dwell time and visitor density And combine these behavior data with the comprehensive environmental parameters of the exhibition hall, such as temperature T, humidity H, and light intensity L, to generate visitor behavior and environment dataset B; S42. The system dynamically calculates the environmental adjustment weight W of each area in the exhibition hall based on the visitor behavior and environmental data set B. By combining the visitor's behavior pattern and the current environmental parameters, the system can intelligently identify the actual needs of each area: ; in, is the environmental adjustment weight of the ith region, is the weight coefficient of visitor behavior data, is the weight coefficient of the environmental parameters, , , are the visitor behavior data in the i-th area; S43. Based on the calculated environmental adjustment weight W, the system dynamically adjusts the temperature of each area in the exhibition hall. and lighting intensity , adapting the environment of each area to the needs of visitors: ; ; in, is the adjusted temperature, is the adjusted lighting intensity, and is the adjustment coefficient; S44. The system uses a feedback mechanism to update visitor behavior data and environmental parameters in real time, and optimizes temperature and lighting control based on the latest data to achieve dynamic closed-loop management.

[0011] Optionally, the S5 specifically includes: S51. The environmental parameters in the exhibition hall are monitored in real time through the intelligent anomaly detection module, including temperature T, humidity H, light intensity L, equipment operation status S, and other related equipment data. The system detects whether there is abnormal fluctuation based on the deviation between the dynamic threshold and the actual detection value, and generates an abnormal data set E; S52: When an abnormal data set E is detected, the system classifies the abnormal data through a multi-layer abnormal analysis algorithm, identifies the abnormal source and its impact mode, and generates a fault isolation signal based on the analysis results. : ; in, is the fault isolation factor, is the abnormal data point at time t, is the weight coefficient, It is the exception mode function; S53, based on fault isolation signal , the system automatically adjusts the operating parameters of other equipment to maintain the stability of the overall exhibition hall environment: ; in, is the control parameter of the current device, is the adjusted device control parameter, To adjust the rate, To adjust the sensitivity coefficient, is the change amount of abnormal data; S54. The system continuously monitors the equipment operating status and environmental parameters through a closed-loop feedback mechanism, allowing other equipment to operate adaptively after fault isolation, while regularly optimizing fault detection and isolation strategies.

[0012] Optionally, the S6 specifically includes: S61. Based on the abnormal analysis results and the current energy consumption status of the exhibition hall, the system monitors the power output of each device in the exhibition hall in real time. , key environmental parameters and visitor density , generate a comprehensive energy consumption dataset ; S62, combined with equipment control parameters and comprehensive environmental parameters, the system uses a long-term energy consumption optimization learning algorithm to optimize the comprehensive energy consumption data set. Perform analysis and calculate equipment power optimization weights , dynamically adjust the power output of the equipment; S63, when the density of visitors is detected When increasing, the system optimizes the weight according to the power , dynamically improve equipment power output: ; in, is the adjusted device power output, is the power adjustment rate, is the adjustment coefficient, Adjust thresholds for visitor density; S64. When the visitor density When it is reduced, the system reduces the power output of the equipment, reduces unnecessary energy consumption, and optimizes the overall energy efficiency management of the exhibition hall; S65. Through historical data analysis and long-term energy consumption optimization learning algorithms, the system regularly optimizes the equipment power output strategy to achieve energy-saving management of the exhibition hall.

[0013] Optionally, the S7 specifically includes: S71, the system uses an adaptive learning module based on historical operation data , visitor behavior data B and abnormal data E, continuously collect multi-dimensional information in the exhibition hall, generate and update the comprehensive data set in real time ; S72, the system is based on a comprehensive data set , through adaptive learning algorithms, dynamically optimize the equipment control model M, which can analyze current data and combine trends in historical data to make long-term and short-term behavior predictions: ; in, is the equipment control model at time t, is the adaptive learning rate, is the optimization function based on the current data set, Long- and short-term behavior patterns extracted based on historical data; S73, the system is based on the optimized control model , combining the long-term operation status in the exhibition hall and the behavior patterns of visitors, generating equipment control parameters in real time : ; in, is the device control parameter at time t, is the initial control parameter of the device, is the adjustment factor, The amount of change in the equipment control model; S74. The system continuously monitors the equipment operation status and visitor behavior data through the feedback mechanism to form a feedback data set ,The feedback mechanism updates the equipment control model based on real-time data; S75. Based on the adaptive learning and feedback optimization mechanism, the system can automatically optimize the operation strategy of the equipment, the balance between energy efficiency management and visitor experience according to the dynamic changes of the exhibition hall in the long run, and realize the long-term self-optimization of the exhibition hall environment.

[0014] Optional modules include: Adaptive multimodal sensor network module: collects temperature, humidity, light intensity, noise, air quality and personnel flow data in the exhibition hall, and dynamically adjusts the sampling frequency and priority; IoT node module: transmits environmental data to the central processing module to realize data collection and remote transmission; Central processing module: Based on historical data, real-time data and visitor behavior data, it uses time series multidimensional regression analysis or adaptive learning algorithm to optimize equipment control parameters; Multi-source data fusion module: integrates sensor data, generates comprehensive environmental parameters, and optimizes equipment operation mode; Visitor behavior perception module: monitors visitor movement trajectory, residence time and density, and optimizes equipment parameters based on environmental data; Intelligent anomaly detection module: monitors the environment and equipment status, detects anomalies and isolates faults; Energy consumption optimization module: dynamically adjusts equipment power output and optimizes energy efficiency management based on energy consumption status and equipment control parameters; Adaptive learning module: Through historical and real-time data, it continuously optimizes the equipment control model, automatically adjusts the equipment operation strategy, and achieves long-term self-optimization of the exhibition hall.

[0015] The beneficial effects of the present invention are: The present invention solves the problems of low equipment control efficiency, high energy consumption and untimely fault detection in the existing exhibition hall environment management by combining the Internet of Things technology with the multimodal sensor network. The adaptive multimodal sensor network can collect temperature, humidity, light intensity, noise, air quality and personnel flow data in the exhibition hall in real time. The sensor network is based on a multi-dimensional data mutation monitoring algorithm and has the ability to automatically adjust the sampling frequency and priority, thereby achieving more accurate environmental monitoring and rapid response.

[0016] The present invention performs multi-source data fusion on the collected data through the central processing module, combines historical operation data with real-time collected data, and uses an improved time series multidimensional regression analysis algorithm to dynamically predict the trend of exhibition hall environment changes and generate real-time equipment control parameters. Through this optimization method, the system can automatically adjust the temperature, lighting and other parameters in the exhibition hall according to environmental changes to ensure that the exhibition hall environment is always in the best state, which not only improves the visitor experience, but also improves the intelligence level of equipment operation. In terms of energy consumption management, the present invention adopts a long-term energy consumption optimization learning algorithm to dynamically adjust the power output of each device in the exhibition hall. The system optimizes the equipment power consumption according to the visitor density, environmental parameters and equipment status, which not only ensures the normal operation of the equipment when the visitors are dense, but also reduces the equipment power consumption when the visitors are small, thereby significantly improving energy efficiency, reducing energy waste, and solving the problem of insufficient energy consumption optimization in the prior art.

[0017] In terms of equipment safety, the present invention introduces an intelligent anomaly detection and fault isolation module to monitor the equipment operating status in real time, quickly detect and isolate the source of the fault, and avoid the overall failure of the system due to a single equipment failure. The system continuously monitors the operating status and environmental data of the equipment through a closed-loop feedback mechanism, so that the system can adaptively adjust the operating mode of other equipment after a fault occurs to maintain the stability of the overall exhibition hall environment. The present invention continuously optimizes the equipment control model through an adaptive learning module, and dynamically adjusts the equipment operation strategy based on historical operating data, behavioral data and abnormal data. The feedback optimization mechanism enables the system to have self-learning and adjustment capabilities, and can achieve long-term self-optimization of the exhibition hall environment and equipment management according to the long-term operating status of the exhibition hall and the behavior patterns of visitors. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] 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: Figure 1 This is a flow chart of an exhibition hall intelligent control system and method based on Internet of Things technology proposed by the present invention; Figure 2 It is a data collection flow chart of the adaptive multimodal sensor network in the present invention; Figure 3 This is a workflow diagram of the energy consumption optimization module in the present invention. DETAILED DESCRIPTION

[0019] 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.

[0020] refer to Figure 1-3, an exhibition hall intelligent control system and method based on Internet of Things technology, comprising the following steps: S1. Collect environmental data in the exhibition hall through an adaptive multimodal sensor network. The environmental data includes temperature, humidity, light intensity, noise, air quality and personnel flow data. The sensor network dynamically adjusts the sampling frequency and priority of the sensor through a multi-dimensional data mutation monitoring algorithm; S2. The collected environmental data is transmitted to the central processing module through the Internet of Things node. The central processing module combines the historical operation data with the real-time collected data and uses the improved time series multidimensional regression analysis algorithm to build an environmental change prediction model. The algorithm analyzes the time series data of temperature and humidity, personnel flow and equipment operation status, combines nonlinear multidimensional regression analysis, dynamically calculates the environmental change trend, and generates real-time equipment control parameters; S3, using the generated real-time device control parameters, and processing the multi-dimensional environmental data obtained by different sensors in real time through a multi-source data fusion algorithm to generate comprehensive environmental parameters; S4. Based on comprehensive environmental parameters and visitor behavior perception modules, the movement trajectory, residence time and density information of visitors are monitored in real time. The system dynamically adjusts the temperature and lighting parameters of relevant areas in the exhibition hall according to the visitor behavior data and comprehensive environmental parameters to optimize the personalized environmental experience of visitors; S5. When the system detects abnormalities in the monitored environmental parameters and equipment operating status, it uses the intelligent anomaly detection and fault isolation module to analyze the abnormal data, identify and isolate the source of the fault. The system adjusts the operating mode of other equipment based on the abnormal analysis results to maintain the overall environmental stability of the exhibition hall and the safety of the equipment; S6. Based on the abnormal analysis results and the current energy consumption status of the system, combined with the equipment control parameters and comprehensive environmental parameters, the system dynamically adjusts the power output of each device in the exhibition hall through a long-term energy consumption optimization learning algorithm. The system gives priority to ensuring the normal operation of the equipment when the number of visitors is dense, and reduces the power consumption of the equipment when the number of visitors decreases, thus realizing the energy efficiency management and energy saving optimization of the exhibition hall; S7. Through the feedback optimization mechanism, the system dynamically adjusts the equipment's operating strategy based on historical operating data, behavioral data and abnormal data, and combines long-term and short-term environmental change patterns with equipment status feedback to achieve long-term self-optimization of the exhibition hall environment.

[0021] In this implementation, S1 specifically includes: S11, configuring an adaptive multimodal sensor network, wherein the sensors include a temperature sensor T, a humidity sensor H, a light sensor L, a noise sensor N, an air quality sensor A, and a personnel flow sensor P, which are respectively arranged in multiple key areas of the exhibition hall to collect environmental data in real time according to the fluctuation characteristics of different environmental parameters in the exhibition hall; S12, set the initial sampling frequency of each sensor , , , , and ,in , , , , and The sampling frequencies for temperature, humidity, light, noise, air quality and personnel flow are respectively set at once per minute, and can be adaptively adjusted based on real-time fluctuation data through the central control module; S13, by analyzing the real-time collected environmental data, combined with the multi-dimensional mutation detection algorithm, dynamically calculate the sampling priority and , , , , and : ; in, is the change of environmental parameter X, is the weight factor, To adjust the constant, is the sampling priority of sensor X; S14, when the priority When the preset threshold is reached, the central processing module automatically and dynamically adjusts the sampling frequency of the corresponding sensor through the adaptive sampling adjustment mechanism : ; in, is the current sampling frequency, is the adjusted sampling frequency, is the sensitivity coefficient, k is the adjustment rate, is the change threshold; S15, according to the adjusted sampling frequency ,The sensor network continuously collects and transmits environmental data, which are transmitted to the central processing module through the Internet of Things nodes to generate the exhibition hall environment data set D.

[0022] In this implementation, S2 specifically includes: S21, transmitting the environmental data set D to the central processing module through the Internet of Things node, and generating a joint data set D' in combination with the historical operation data, wherein the joint data set D' includes all real-time and historical environmental data in the exhibition hall; S23, the central processing module uses the improved time series multidimensional regression analysis algorithm to build an environmental change prediction model based on the joint data set D', and analyzes the change trend of environmental parameters by combining time series data and nonlinear regression: ; in, To predict the environmental change value at the future time t+1, is the regression coefficient, is the environmental data at time t, is the nonlinear regression function, is the time correlation coefficient, is the nonlinear characteristic function describing time variation, is the error term; S24. In the environmental change prediction model, the input data includes temperature and humidity data T, H, personnel flow data P and equipment operation status , by analyzing the time correlation of each parameter, a real-time prediction model is generated: ; in, is the predicted temperature at the next moment, is the temperature change at time t, are the weights of different parameters, is a nonlinear function; S25. Based on the predicted environmental change value, the central processing module generates the equipment control parameter C. The control parameter comprehensively considers temperature, humidity, personnel flow and equipment operation status through the optimization formula: ; Among them, C is the device control parameter, is the weight coefficient of each environmental parameter, is a nonlinear function that describes environmental changes.

[0023] In this implementation manner, the S4 specifically includes: S41. Monitor the movement trajectory of visitors in real time through the visitor behavior perception module , Dwell time and visitor density And combine these behavior data with the comprehensive environmental parameters of the exhibition hall, such as temperature T, humidity H, and light intensity L, to generate visitor behavior and environment dataset B; S42. The system dynamically calculates the environmental adjustment weight W of each area in the exhibition hall based on the visitor behavior and environmental data set B. By combining the visitor's behavior pattern and the current environmental parameters, the system can intelligently identify the actual needs of each area: ; in, is the environmental adjustment weight of the ith region, is the weight coefficient of visitor behavior data, is the weight coefficient of the environmental parameters, , , are the visitor behavior data in the i-th area; S43. Based on the calculated environmental adjustment weight W, the system dynamically adjusts the temperature of each area in the exhibition hall. and lighting intensity , adapting the environment of each area to the needs of visitors: ; ; in, is the adjusted temperature, is the adjusted lighting intensity, and is the adjustment coefficient; S44. The system uses a feedback mechanism to update visitor behavior data and environmental parameters in real time, and optimizes temperature and lighting control based on the latest data to achieve dynamic closed-loop management.

[0024] In this implementation manner, S5 specifically includes: S51. The environmental parameters in the exhibition hall are monitored in real time through the intelligent anomaly detection module, including temperature T, humidity H, light intensity L, equipment operation status S, and other related equipment data. The system detects whether there is abnormal fluctuation based on the deviation between the dynamic threshold and the actual detection value, and generates an abnormal data set E; S52: When an abnormal data set E is detected, the system classifies the abnormal data through a multi-layer abnormal analysis algorithm, identifies the abnormal source and its impact mode, and generates a fault isolation signal based on the analysis results. : ; in, is the fault isolation factor, is the abnormal data point at time t, is the weight coefficient, It is the exception mode function; S53, based on fault isolation signal , the system automatically adjusts the operating parameters of other equipment to maintain the stability of the overall exhibition hall environment: ; in, is the control parameter of the current device, is the adjusted device control parameter, To adjust the rate, To adjust the sensitivity coefficient, is the change amount of abnormal data; S54. The system continuously monitors the equipment operating status and environmental parameters through a closed-loop feedback mechanism, allowing other equipment to operate adaptively after fault isolation, while regularly optimizing fault detection and isolation strategies.

[0025] In this implementation manner, S6 specifically includes: S61. Based on the abnormal analysis results and the current energy consumption status of the exhibition hall, the system monitors the power output of each device in the exhibition hall in real time. , key environmental parameters and visitor density , generate a comprehensive energy consumption dataset ; S62, combined with equipment control parameters and comprehensive environmental parameters, the system uses a long-term energy consumption optimization learning algorithm to optimize the comprehensive energy consumption data set. Perform analysis and calculate equipment power optimization weights , dynamically adjust the power output of the equipment; S63, when the density of visitors is detected When increased, the system optimizes the weight according to power , dynamically improve equipment power output: ; in, is the adjusted device power output, is the power adjustment rate, is the adjustment coefficient, Adjust thresholds for visitor density; S64. When the visitor density When it is reduced, the system reduces the power output of the equipment, reduces unnecessary energy consumption, and optimizes the overall energy efficiency management of the exhibition hall; S65. Through historical data analysis and long-term energy consumption optimization learning algorithms, the system regularly optimizes the equipment power output strategy to achieve energy-saving management of the exhibition hall.

[0026] In this implementation manner, the S7 specifically includes: S71, the system uses an adaptive learning module based on historical operation data , visitor behavior data B and abnormal data E, continuously collect multi-dimensional information in the exhibition hall, generate and update the comprehensive data set in real time ; S72, the system is based on a comprehensive data set , through adaptive learning algorithms, dynamically optimize the equipment control model M, which can analyze current data and combine trends in historical data to make long-term and short-term behavior predictions: ; in, is the equipment control model at time t, is the adaptive learning rate, is the optimization function based on the current data set, Long- and short-term behavior patterns extracted based on historical data; S73, the system is based on the optimized control model , combining the long-term operation status in the exhibition hall and the behavior patterns of visitors, generating equipment control parameters in real time : ; in, is the device control parameter at time t, is the initial control parameter of the device, is the adjustment factor, The amount of change in the equipment control model; S74. The system continuously monitors the equipment operation status and visitor behavior data through the feedback mechanism to form a feedback data set ,The feedback mechanism updates the equipment control model based on real-time data; S75. Based on the adaptive learning and feedback optimization mechanism, the system can automatically optimize the operation strategy of the equipment, the balance between energy efficiency management and visitor experience according to the dynamic changes of the exhibition hall in the long run, and realize the long-term self-optimization of the exhibition hall environment.

[0027] In this embodiment, the following modules are included: Adaptive multimodal sensor network module: collects temperature, humidity, light intensity, noise, air quality and personnel flow data in the exhibition hall, and dynamically adjusts the sampling frequency and priority; IoT node module: transmits environmental data to the central processing module to realize data collection and remote transmission; Central processing module: Based on historical data, real-time data and visitor behavior data, it uses time series multidimensional regression analysis or adaptive learning algorithm to optimize equipment control parameters; Multi-source data fusion module: integrates sensor data, generates comprehensive environmental parameters, and optimizes equipment operation mode; Visitor behavior perception module: monitors visitor movement trajectory, residence time and density, and optimizes equipment parameters based on environmental data; Intelligent anomaly detection module: monitors the environment and equipment status, detects anomalies and isolates faults; Energy consumption optimization module: dynamically adjusts equipment power output and optimizes energy efficiency management based on energy consumption status and equipment control parameters; Adaptive learning module: Through historical and real-time data, it continuously optimizes the equipment control model, automatically adjusts the equipment operation strategy, and achieves long-term self-optimization of the exhibition hall.

[0028] Embodiment 1: In order to verify the feasibility of the present invention in implementation, the present invention is applied to the intelligent control system of a large exhibition hall. The existing equipment management has problems such as serious energy waste, poor visitor experience, frequent equipment operation failures, etc. In order to improve energy utilization efficiency, enhance visitors' exhibition experience and reduce the impact of equipment failures, we decided to apply the exhibition hall intelligent control system based on the Internet of Things technology of the present invention in the exhibition hall to solve these problems.

[0029] During the exhibition layout process, the exhibition hall covers an area of ​​about 5,000 square meters, including multiple exhibition areas with different functions, such as art exhibition area, interactive experience area and leisure area. The exhibition hall is equipped with various energy-consuming equipment such as air-conditioning system, lighting system, ventilation equipment, etc. The exhibition hall receives about 2,000 visitors every day. The mobility of visitors is strong, especially during peak hours. The density of visitors in some areas is high, while other areas are relatively empty, resulting in the lack of pertinence in the power output of air-conditioning, lighting and other equipment, and a large waste of energy.

[0030] In order to solve this problem, the exhibition hall introduced the intelligent control system of the present invention, which monitors the environmental data in the exhibition hall in real time through an adaptive multimodal sensor network, including temperature, humidity, light intensity, noise, air quality and personnel flow. The system automatically adjusts the sampling frequency of the sensor according to the changes in environmental parameters, and transmits the collected data to the central processing module through the Internet of Things node. Through the accumulation of historical data, the central processing module can build an environmental change prediction model based on the time series multidimensional regression analysis algorithm, predict the environmental change trend of the exhibition hall in different time periods, and generate real-time equipment control parameters. This process is carried out two hours before the opening of the exhibition hall. By preprocessing the early environmental data, the system can reasonably predict the visitor density and equipment demand during the opening period.

[0031] As the exhibition hall opened, visitors began to enter the exhibition hall. Through the visitor behavior perception module, the system monitors the movement trajectory, residence time and density information of each exhibition area in real time. The system will combine the visitor behavior data with the environmental data for real-time analysis. Taking the interactive experience area as an example, when the visitor density in this area increases rapidly, the system generates comprehensive environmental parameters through a multi-source data fusion algorithm, and dynamically adjusts the air conditioning system and lighting intensity of the area according to these parameters to ensure that visitors can still enjoy a comfortable environment experience under high density conditions; data shows that when the visitor density in this area increases from 5 people per square meter to 15 people per square meter, the air conditioning power increases dynamically from the original 20 kilowatts to 45 kilowatts, ensuring that the room temperature is maintained at a comfortable 23 degrees Celsius. The lighting brightness also increases accordingly, reaching the standard of 500 lux per square meter, while the relatively empty exhibition area reduces the lighting and air conditioning power output through the automatic adjustment system to reduce unnecessary energy consumption.

[0032] In actual applications, the energy consumption optimization module will also dynamically adjust the power output of each device in the exhibition hall through a long-term energy consumption optimization learning algorithm. The peak visiting period of the interactive experience area lasts from 10 am to 2 pm, while there are fewer visitors in other periods. By learning this rule, the system can automatically adjust the power output of equipment in different periods. When the peak visiting period ends, the system automatically reduces the air-conditioning power of the interactive experience area to 15 kilowatts and reduces the lighting brightness accordingly. During the one-month test, the overall energy consumption in the exhibition hall decreased by about 20% compared with the original system. Data shows that in the past week, the average daily electricity consumption has been reduced from the original 3200 kWh to 2560 kWh. The dynamic adjustment during peak hours reduced power consumption by about 10%, while the intelligent regulation during non-peak hours saved about 8% of energy consumption.

[0033] The intelligent anomaly detection and fault isolation module played an important role when equipment in the exhibition hall failed. During the implementation process, some equipment in the air-conditioning system experienced abnormal local temperature rise due to long-term operation. The system monitored environmental parameters in real time and found that the temperature in a certain area suddenly rose to 30 degrees Celsius and the humidity dropped to below 40%, which was quite different from the temperature and humidity in other areas. The intelligent anomaly detection module immediately generated an abnormal data set and identified the source of the equipment failure through a multi-layer anomaly analysis algorithm. The system automatically adjusted the operating mode of other equipment to maintain the stability of the overall environment, while isolating the faulty equipment to ensure the normal operation of equipment in other areas of the exhibition hall. Data showed that during the equipment failure, the overall temperature fluctuation was controlled within the range of ±2 degrees Celsius, and fault detection and isolation were completed within 15 minutes, without negatively affecting the visitor experience.

[0034] Within one month of implementation, the smart control system successfully solved problems such as low efficiency in energy management of the exhibition hall, poor visitor experience and untimely equipment fault detection. Through long-term data accumulation and feedback optimization mechanism, the system continuously optimized the equipment's operation strategy, realized intelligent energy management and improved visitor experience. The exhibition hall's daily visitor satisfaction survey showed that 90% of visitors were satisfied with the environmental comfort of the exhibition hall, and the overall energy efficiency level of the exhibition hall was also significantly improved.

[0035] Table 1 Energy efficiency management data table of the interactive experience area of ​​the exhibition hall

[0036] According to the above table, it can be clearly shown that the system can improve the energy efficiency of equipment operation and the comfort of visitors through intelligent monitoring and dynamic adjustment in different time periods. From the data, it can be seen that when the visitor density is high, the system can quickly increase the power output of the equipment to ensure that the lighting, temperature and air quality are in the best state. When the number of visitors decreases, the system effectively reduces unnecessary equipment operation power through the dynamic energy consumption optimization algorithm, thereby significantly reducing energy consumption. This adaptive adjustment capability not only ensures the normal operation of the exhibition hall, but also achieves significant energy-saving effects in energy efficiency management. The energy consumption adjustment ratio under different visitor densities varies significantly, especially during peak hours, when the power output of the equipment responds quickly with the increase in visitors, improving the efficiency of the equipment. During the low-density visit period, the system reduces the power output of the equipment and achieves a 10%-20% reduction in energy consumption, thereby achieving the goal of energy saving. In addition, environmental parameters such as temperature, humidity and air quality are stabilized under intelligent adjustment and fully match the system optimization strategy, which greatly improves the visitor experience and greatly improves the stability of equipment operation.

[0037] To sum up, the present invention effectively improves the level of automated management of the exhibition hall environment. It not only realizes precise environmental monitoring and intelligent control, but also greatly reduces the energy consumption of equipment operation, improves the safety and stability of the system, and solves the problems of low equipment control efficiency, high energy consumption and untimely fault detection in the prior art. It has significant practical value and economic benefits.

[0038] 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 smart exhibition hall control method based on Internet of Things technology, characterized in that: The steps include: S1, collect environmental data in the exhibition hall through an adaptive multimodal sensor network; S2. Combining historical operation data with real-time environmental data, using an improved time series multidimensional regression analysis algorithm to build an environmental change prediction model and generate real-time equipment control parameters; S3, using the generated real-time device control parameters, and processing the multi-dimensional environmental data obtained by different sensors in real time through a multi-source data fusion algorithm to generate comprehensive environmental parameters; S4. Based on comprehensive environmental parameters and visitor behavior perception modules, the movement trajectory, residence time and density information of visitors are monitored in real time. The system dynamically adjusts the temperature and lighting parameters of relevant areas in the exhibition hall according to the visitor behavior data combined with comprehensive environmental parameters; S5. When the system detects abnormalities in the monitored environmental parameters and equipment operating status, it uses the intelligent anomaly detection and fault isolation module to analyze the abnormal data, identify and isolate the fault source, and adjust the operating mode of other equipment according to the abnormal analysis results; S6. Based on the abnormal analysis results and the current energy consumption status of the system, combined with the equipment control parameters and comprehensive environmental parameters; S7. The system dynamically adjusts the equipment's operating strategy based on historical operating data, behavioral data, and abnormal data through a feedback optimization mechanism.

2. According to claim 1, a smart exhibition hall control method based on Internet of Things technology is characterized in that: The S1 specifically includes: S11, configuring an adaptive multimodal sensor network, wherein the sensors include a temperature sensor T, a humidity sensor H, a light sensor L, a noise sensor N, an air quality sensor A, and a personnel flow sensor P, which are respectively arranged in multiple key areas of the exhibition hall to collect environmental data in real time according to the fluctuation characteristics of different environmental parameters in the exhibition hall; S12, set the initial sampling frequency of each sensor , , , , and ,in , , , , and The sampling frequencies for temperature, humidity, light, noise, air quality and personnel flow are respectively set at once per minute, and can be adaptively adjusted based on real-time fluctuation data through the central control module; S13, by analyzing the real-time collected environmental data, combined with the multi-dimensional mutation detection algorithm, dynamically calculate the sampling priority and , , , , and : ； in, is the change of environmental parameter X, is the weight factor, To adjust the constant, is the sampling priority of sensor X; S14, when the priority When the preset threshold is reached, the central processing module automatically and dynamically adjusts the sampling frequency of the corresponding sensor through the adaptive sampling adjustment mechanism : ； in, is the current sampling frequency, is the adjusted sampling frequency, is the sensitivity coefficient, k is the adjustment rate, is the change threshold; S15, according to the adjusted sampling frequency ,The sensor network continuously collects and transmits environmental data, which are transmitted to the central processing module through the Internet of Things nodes to generate the exhibition hall environment data set D.

3. The exhibition hall intelligent control method based on Internet of Things technology according to claim 1 is characterized in that: The S2 specifically includes: S21, transmitting the environmental data set D to the central processing module through the Internet of Things node, and generating a joint data set D' in combination with the historical operation data, wherein the joint data set D' includes all real-time and historical environmental data in the exhibition hall; S23, the central processing module uses the improved time series multidimensional regression analysis algorithm to build an environmental change prediction model based on the joint data set D', and analyzes the change trend of environmental parameters by combining time series data and nonlinear regression: ； in, To predict the environmental change value at the future time t+1, is the regression coefficient, is the environmental data at time t, is the nonlinear regression function, is the time correlation coefficient, is a nonlinear characteristic function describing time variation, is the error term; S24. In the environmental change prediction model, the input data includes temperature and humidity data T, H, personnel flow data P and equipment operation status , by analyzing the time correlation of each parameter, a real-time prediction model is generated: ； in, is the predicted temperature at the next moment, is the temperature change at time t, are the weights of different parameters, is a nonlinear function; S25. Based on the predicted environmental change value, the central processing module generates the equipment control parameter C. The control parameter comprehensively considers temperature, humidity, personnel flow and equipment operation status through the optimization formula: ； Among them, C is the device control parameter, is the weight coefficient of each environmental parameter, is a nonlinear function that describes environmental changes.

4. The exhibition hall intelligent control method based on Internet of Things technology according to claim 1 is characterized in that: The S4 specifically includes: S41. Monitor the movement trajectory of visitors in real time through the visitor behavior perception module , Dwell time and visitor density And combine these behavior data with the comprehensive environmental parameters of the exhibition hall, such as temperature T, humidity H, and light intensity L, to generate visitor behavior and environment dataset B; S42. The system dynamically calculates the environmental adjustment weight W of each area in the exhibition hall based on the visitor behavior and environmental data set B. By combining the visitor's behavior pattern and the current environmental parameters, the system can intelligently identify the actual needs of each area: ； in, is the environmental adjustment weight of the ith region, is the weight coefficient of visitor behavior data, is the weight coefficient of the environmental parameters, , , are the visitor behavior data in the i-th area; S43. Based on the calculated environmental adjustment weight W, the system dynamically adjusts the temperature of each area in the exhibition hall. and lighting intensity , adapting the environment of each area to the needs of visitors: ； ； in, is the adjusted temperature, is the adjusted lighting intensity, and is the adjustment coefficient; S44. The system uses a feedback mechanism to update visitor behavior data and environmental parameters in real time, and optimizes temperature and lighting control based on the latest data to achieve dynamic closed-loop management.

5. The exhibition hall intelligent control method based on Internet of Things technology according to claim 1 is characterized in that: The S5 specifically includes: S51. The environmental parameters in the exhibition hall are monitored in real time through the intelligent anomaly detection module, including temperature T, humidity H, light intensity L, equipment operation status S, and other related equipment data. The system detects whether there is abnormal fluctuation based on the deviation between the dynamic threshold and the actual detection value, and generates an abnormal data set E; S52: When an abnormal data set E is detected, the system classifies the abnormal data through a multi-layer abnormal analysis algorithm, identifies the abnormal source and its impact mode, and generates a fault isolation signal based on the analysis results. : ； in, is the fault isolation factor, is the abnormal data point at time t, is the weight coefficient, It is the exception mode function; S53, based on fault isolation signal , the system automatically adjusts the operating parameters of other equipment to maintain the stability of the overall exhibition hall environment: ； in, is the control parameter of the current device, is the adjusted device control parameter, To adjust the rate, To adjust the sensitivity coefficient, is the change amount of abnormal data; S54. The system continuously monitors the equipment operating status and environmental parameters through a closed-loop feedback mechanism, allowing other equipment to operate adaptively after fault isolation, while regularly optimizing fault detection and isolation strategies.

6. The exhibition hall intelligent control method based on Internet of Things technology according to claim 1 is characterized in that: The S6 specifically includes: S61. Based on the abnormal analysis results and the current energy consumption status of the exhibition hall, the system monitors the power output of each device in the exhibition hall in real time. , key environmental parameters and visitor density , generate a comprehensive energy consumption dataset ; S62, combined with equipment control parameters and comprehensive environmental parameters, the system uses a long-term energy consumption optimization learning algorithm to optimize the comprehensive energy consumption data set. Perform analysis and calculate equipment power optimization weights , dynamically adjust the power output of the equipment; S63, when the density of visitors is detected When increased, the system optimizes the weight according to power , dynamically improve equipment power output: ； in, is the adjusted device power output, is the power adjustment rate, is the adjustment coefficient, Adjust thresholds for visitor density; S64. When the visitor density When it is reduced, the system reduces the power output of the equipment, reduces unnecessary energy consumption, and optimizes the overall energy efficiency management of the exhibition hall; S65. Through historical data analysis and long-term energy consumption optimization learning algorithms, the system regularly optimizes the equipment power output strategy to achieve energy-saving management of the exhibition hall.

7. The exhibition hall intelligent control method based on Internet of Things technology according to claim 1 is characterized in that: The S7 specifically includes: S71, the system uses an adaptive learning module based on historical operation data , visitor behavior data B and abnormal data E, continuously collect multi-dimensional information in the exhibition hall, generate and update the comprehensive data set in real time ; S72, the system is based on a comprehensive data set , through adaptive learning algorithms, dynamically optimize the equipment control model M, which can analyze current data and combine trends in historical data to make long-term and short-term behavior predictions: ； in, is the equipment control model at time t, is the adaptive learning rate, is the optimization function based on the current data set, Long- and short-term behavior patterns extracted based on historical data; S73, the system is based on the optimized control model , combining the long-term operation status in the exhibition hall and the behavior patterns of visitors, generating equipment control parameters in real time : ； in, is the device control parameter at time t, is the initial control parameter of the device, is the adjustment factor, The amount of change in the equipment control model; S74. The system continuously monitors the equipment operation status and visitor behavior data through the feedback mechanism to form a feedback data set ,The feedback mechanism updates the equipment control model based on real-time data; S75. Based on the adaptive learning and feedback optimization mechanism, the system can automatically optimize the operation strategy of the equipment, the balance between energy efficiency management and visitor experience according to the dynamic changes of the exhibition hall in the long run, and realize the long-term self-optimization of the exhibition hall environment.

8. An exhibition hall intelligent control system based on Internet of Things technology, characterized in that: Includes the following modules: Adaptive multimodal sensor network module: collects temperature, humidity, light intensity, noise, air quality and personnel flow data in the exhibition hall, and dynamically adjusts the sampling frequency and priority; IoT node module: transmits environmental data to the central processing module to realize data collection and remote transmission; Central processing module: Based on historical data, real-time data and visitor behavior data, it uses time series multidimensional regression analysis or adaptive learning algorithms to optimize equipment control parameters; Multi-source data fusion module: integrates sensor data, generates comprehensive environmental parameters, and optimizes equipment operation mode; Visitor behavior perception module: monitors visitor movement trajectory, residence time and density, and optimizes equipment parameters based on environmental data; Intelligent anomaly detection module: monitors the environment and equipment status, detects anomalies and isolates faults; Energy consumption optimization module: dynamically adjusts equipment power output and optimizes energy efficiency management based on energy consumption status and equipment control parameters; Adaptive learning module: Through historical and real-time data, it continuously optimizes the equipment control model, automatically adjusts the equipment operation strategy, and achieves long-term self-optimization of the exhibition hall.

Images