Wireless transmission temperature intelligent adjusting system and method in tent

Abstract

The invention provides a wireless transmission temperature intelligent adjusting system and method in a tent, and belongs to the technical field of intelligent temperature adjustment. The wireless transmission temperature intelligent adjusting system in the tent comprises a central control unit; the temperature sensor module is connected with the central control unit through a wireless transmission module; the heating and cooling device is in signal connection with the central control unit; by using the scheme, the temperature, humidity and other conditions in the tent are wirelessly and intelligently controlled, the temperature in the tent is adjusted in time, the temperature in the tent is appropriate even in hot summer and cold winter, the tent is suitable for living and activities of people, and the tent is controlled through a mobile phone APP and is easy and convenient to operate.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent temperature regulation, and specifically relates to a wireless transmission intelligent temperature regulation system and method in a tent; Background Art

[0002] Temperature control in a tent is an issue that requires comprehensive consideration of environmental factors and tent materials. By controlling the temperature in a tent, a more livable environment can be created, ensuring the comfort of campers regardless of overheating or overcooling. At a suitable temperature, people are more likely to fall asleep and get high-quality sleep, which is essential for restoring physical strength and enjoying camping activities. Extreme temperatures may have adverse effects on health, such as heat stroke and frostbite. By controlling the temperature in a tent, these health risks can be reduced. Using appropriate temperature control equipment in a tent, such as heaters or cooling equipment, can reduce safety accidents such as fires and carbon monoxide poisoning caused by overheating or cold. Good temperature control can allow campers to focus more on enjoying outdoor activities, such as hiking, fishing, stargazing, etc., rather than being bothered by uncomfortable temperatures.

[0003] In the prior art, there is no temperature control system in the traditional tent. The temperature in the tent is determined by the material of the tent. If the tent has good ventilation and sun protection, the temperature in the tent will be kept comfortable. However, in hot or cold weather, the temperature in the tent can no longer be adjusted by the material and ventilation of the tent. Such weather is not suitable for people to live in tents. Summary of the invention

[0004] The purpose of the present invention is to provide a wireless transmission temperature intelligent adjustment system and method in a tent, aiming to solve the problem that there is no temperature control system in a traditional tent in the prior art, and the temperature in the tent is determined by the material of the tent. If the tent has good ventilation and sun protection effect, the temperature in the tent will be kept comfortable. However, in hot or cold weather, the temperature in the tent can no longer be adjusted by the material and ventilation of the tent, and such weather is not suitable for people to live in the tent.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A wireless transmission temperature intelligent regulation system in a tent, comprising:

[0007] Central control unit;

[0008] A temperature sensor module, wherein the temperature sensor module is connected to the central control unit via a wireless transmission module;

[0009] A heating and cooling device, the heating and cooling device is connected to the central control unit by signal; and a mobile phone APP, the mobile phone APP is connected to the central control unit by signal;

[0010] As a preferred solution of the present invention, the central control unit includes a microprocessor, a memory and a communication interface;

[0011] As a preferred solution of the present invention, the temperature sensor module includes a plurality of temperature sensors, and the temperature sensors are connected to the central control unit via an independent wireless transmission module;

[0012] As a preferred solution of the present invention, the heating and cooling device comprises a heater and a cooler, and the heater and the cooler are respectively connected to the output signal of the central control unit;

[0013] As a preferred solution of the present invention, the mobile phone APP has the functions of displaying the temperature in the tent in real time, setting the temperature threshold and controlling the heating and cooling devices;

[0014] As a preferred solution of the present invention, the wireless transmission module is a Bluetooth module, which is used to realize wireless communication between the central control unit and the temperature sensor module, the heating and cooling device;

[0015] As a preferred solution of the present invention, the central control unit has the function of automatically adjusting the temperature, humidity and light in the tent;

[0016] As a preferred solution of the present invention, the system further comprises a battery pack, which provides power for the central control unit, the temperature sensor module, the heating and cooling device, the mobile phone APP and the humidity sensor module, and has a long battery life;

[0017] As a preferred solution of the present invention, the wireless transmission temperature intelligent adjustment system in the tent further includes a humidity sensor module, which is connected to the central control unit via the wireless transmission module and is used to monitor the humidity in the tent;

[0018] A method for using a wireless transmission temperature intelligent adjustment system in a tent, comprising the following steps:

[0019] S1. When the user enters the tent, the user sets the ideal temperature range through the user interface of the mobile phone APP;

[0020] S2, the temperature sensor starts working and continuously monitors the ambient temperature, and transmits the data to the central control unit through the wireless module;

[0021] S3, the central control unit compares the real-time temperature data with the temperature range set by the user and makes corresponding adjustments;

[0022] S4. If the temperature is out of range, the control unit will activate the corresponding heating or cooling device until the temperature returns to the set range;

[0023] S5, the control unit regularly analyzes the temperature data to optimize energy efficiency and informs the user of the current temperature status and energy consumption through the user interface;

[0024] As a preferred solution of the present invention, the wireless transmission temperature intelligent adjustment method in the tent receives new environmental data in real time and predicts future temperature and humidity. At the same time, the imitation learning model is iteratively optimized according to user feedback and system performance data. The specific process is as follows;

[0025] Step 1: Data collection;

[0026] Collect real-time data using multiple temperature and humidity sensors in the tent;

[0027] Step 2: Gated recurrent unit prediction;

[0028] The gated recurrent unit is selected as the machine learning model for time series prediction. The trained model is integrated into the central control unit so that it can receive sensor data in real time and predict future environmental changes. The gated recurrent unit is a popular recurrent neural network structure for processing time series data. GRU controls the information flow through two main gating mechanisms: update gate and reset gate. The specific formula is as follows.

[0029] Update Gate:

[0030] z t =σ(W z ·x t +U z ·h t-1 +b z )

[0031] Among them, z t represents the update gate at time step t, σ is the sigmoid function, W z represents the weight matrix of the update gate, x t represents the input vector at the current time step t, U z represents the weight matrix of the update gate, h t-1 represents the hidden state vector of the previous time step t-1, b z represents the bias vector of the update gate;

[0032] Reset the gate:

[0033] r t =σ(W r ·x t +U r ·ht-1 +b r )

[0034] Among them, r t represents the output vector of the reset gate, σ is the sigmoid activation function, and W r represents the weight matrix of the reset gate, x t represents the input vector at the current time step t, h t-1 represents the hidden state vector at the previous time step t-1, U r represents the weight matrix of the reset gate, b r represents the bias vector for the reset gate;

[0035] Candidate hidden states;

[0036]

[0037] represents the candidate hidden state vector, which is the candidate state of the current time step t and contains new information. Tanh represents the hyperbolic tangent activation function. W h Represents the input x for the current time step t t The weight matrix, h t-1 represents the hidden state vector at the previous time step t-1, U h Indicates the previous hidden state h t-1 The weight matrix, r t represents the output vector of the reset gate, ⊙ represents element-by-element multiplication, b h represents the bias vector;

[0038] Final hidden status update:

[0039]

[0040] Among them, h t represents the hidden state vector at the current time step t, z t Represents the output vector of the update gate, 1-z t represents the inverted output of the update gate, h t-1 represents the hidden state vector at the previous time step t-1, represents the candidate hidden state vector at the current time step t;

[0041] Step 3: Imitation learning;

[0042] Collect operational data from experts or experienced users when using the temperature control system in the tent, including how they adjust the temperature settings according to different environmental conditions; this data will serve as the basis for training the imitation learning model; behavioral cloning, to imitate the decision-making process of experts. The behavior cloning learning process is as follows;

[0043] at =π θ (s t )

[0044] Among them, strategy π θ is a neural network, s t represents the state at time step t; a t represents the action selected by the expert at time step t;

[0045]

[0046] Among them, L(θ) is the loss function value under parameter θ, θ represents the parameter of the policy network, and a t Be an expert in status t The next action, π θ (s t ) is the policy model in state s t The predicted action is T, and T is the total number of demonstration data;

[0047] In order for the policy model to predict the expert's actions as accurately as possible, the optimization goal is set to minimize the above loss function:

[0048]

[0049] Among them, θ * Represents the optimal model parameters obtained after optimization; Represents the process of finding the parameter θ so that the loss function L(θ) reaches the minimum value;

[0050] Step 4: Preference adaptation;

[0051] By analyzing the user's behavior and preference settings in the APP, the algorithm automatically learns and presets the temperature and humidity range that the user may like;

[0052] P={p1,p2,...,p n}

[0053] p i =(t i ,h i )

[0054] Among them, P represents the user preference set, n represents the total number of data points, and p i represents the i-th user's response to temperature t i and humidity i preferences;

[0055] C={c1,c2,...,c k}

[0056] c j =(t′j ,h′ j )

[0057] Among them, C represents the preference center, c k represents the kth preference center, c j Represents the temperature t′ of the jth cluster center j and humidity h′ j ;

[0058] The goal of clustering is to minimize the sum of the squared distances of all points to their nearest cluster center, that is, to minimize the objective function:

[0059]

[0060] Where J represents the objective function, which is the sum of the square distances of all points to their nearest cluster centers; n represents the total number of data points; k represents the total number of cluster centers; p i represents the position vector of the i-th data point; c j represents the position vector of the jth cluster center; w ij Represents an indicator variable. If the data point p i belongs to the jth cluster center, then w ij =1; otherwise w ij =0;||p i -c j || 2 Represents data point p i To cluster center c j The square of the Euclidean distance;

[0061] The process of cluster analysis is as follows:

[0062] Step 1: Randomly select k user preferences as the initial cluster center C;

[0063] Step 2: For each user preference p i , find the nearest cluster center c j , and update the indicator variable w ij :

[0064]

[0065] Among them, w ij represents the indicator variable, representing the data point p i Whether to assign to the jth cluster center, if the data point p i belongs to the jth cluster center, then w ij =1, otherwise w ij =0;argmin j |p i -c j ′|| means to find the value such that||pi -c j′ ||The smallest cluster center index j′, i.e. p i Which cluster center is closest to; c j′ represents the most recent cluster center after update, j′ represents the smallest cluster center index, otherwise represents other cases, w ij =0;

[0066] Step 3: Recalculate the center of each cluster to make it the mean of all points in the cluster:

[0067]

[0068] Among them, c j represents the coordinates of the jth cluster center; w ij represents the indicator variable, representing the data point p i Whether to assign to the jth cluster center, if the data point p i belongs to the jth cluster center, then w ij =1, otherwise w ij =0; p i represents the coordinates of the i-th data point; n represents the total number of data points;

[0069] Step 4: Repeat the assignment and update steps until the cluster center no longer changes significantly or reaches the preset number of iterations.

[0070] Compared with the prior art, the present invention has the following beneficial effects:

[0071] 1. In this solution, by using this solution, the temperature, humidity and other conditions in the tent are controlled by wireless intelligent control, and the temperature in the tent is adjusted in time. Even in hot summer and cold winter, the temperature in the tent is suitable for people to live and move around. It is controlled by mobile phone APP, and the operation is simple and convenient;

[0072] 2. In this solution, users can configure system parameters in the APP, such as language selection, unit conversion, network settings, etc.; the APP allows users to set temperature adjustment modes according to personal preferences, such as sleep mode, day mode, etc.; the APP may include fault detection functions that can identify problems in the system and provide corresponding prompts or solutions;

[0073] 3. In this solution, the heating and cooling device includes a heater and a cooler. The heater is used to increase the temperature in the tent, and the cooler is used to reduce the temperature in the tent. Both are controlled by a central control unit. The central control unit continuously receives current temperature data from the temperature sensor and controls the operation of the heating and cooling device according to the temperature conditions.

[0074] 4. In this solution, by using the gated circulation unit to predict temperature and humidity, the system can more accurately predict future environmental changes; this predictive ability enables the system to adjust the temperature in advance, thereby effectively maintaining the comfort level in the tent, even when the external environment changes rapidly; using the imitation learning algorithm, the system can learn the temperature regulation strategies of experts or experienced users under different environmental conditions; this enables the temperature regulation system to automatically adjust its behavior according to actual conditions and adapt to the needs and preferences of different users; intelligent control algorithms can help the system use energy more efficiently; through accurate temperature prediction and adaptive control, the system can avoid unnecessary heating or cooling, thereby reducing energy waste; BRIEF DESCRIPTION OF THE DRAWINGS

[0075] 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:

[0076] Figure 1 It is a structural block diagram of the intelligent adjustment system of the present invention;

[0077] Figure 2 It is a flowchart of the use of the present invention;

[0078] Figure 3 It is a flow chart of the intelligent control algorithm of the present invention; DETAILED DESCRIPTION

[0079] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments; based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present invention;

[0080] In the description of the present invention, it should be noted that the terms "upper", "lower", "inner", "outer", "top / bottom" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the devices or elements referred to must have a specific position, be constructed and operated in a specific position, and therefore cannot be understood as limiting the present invention; in addition, the terms "first" and "second" are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance;

[0081] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "provided with", "mounted / connected", "connected", etc. should be understood in a broad sense. For example, "connected" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be the internal communication of two components; for those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances;

[0082] Example 1

[0083] See also Figure 1-Figure 2 , the present invention provides the following technical solutions:

[0084] A wireless transmission temperature intelligent regulation system in a tent, comprising:

[0085] Central control unit;

[0086] A temperature sensor module, wherein the temperature sensor module is connected to the central control unit via a wireless transmission module;

[0087] a heating and cooling device, the heating and cooling device being in signal connection with the central control unit; and

[0088] A mobile phone APP, wherein the mobile phone APP is connected to the central control unit by signal;

[0089] In a specific embodiment of the present invention, the central control unit is a device integrating a microprocessor, a memory and a communication interface; the temperature sensor module is a plurality of wireless temperature sensors for monitoring the temperature at different positions in the tent; the heating and cooling device is a heater and a cooler for adjusting the temperature in the tent; the mobile phone APP is an application installed on the user's mobile phone for communicating with the central control unit; the central control unit is placed in a suitable position in the tent to ensure that it can be easily connected to the temperature sensor module and the heating and cooling device; the wireless temperature sensor modules are installed at various positions in the tent where the temperature needs to be monitored to ensure that they can cover the temperature requirements of the entire tent; the heater is placed in the position where heating is required in the tent, and the cooler is placed in the position where cooling is required; ensure that they are connected to the central control unit. The wiring is long enough to facilitate wiring; install a battery pack in the tent to provide power for the central control unit, temperature sensor module, heating and cooling device; ensure that the capacity of the battery pack is large enough to meet the long-term operation requirements of the system; use a wireless transmission module to connect the temperature sensor module to the central control unit to ensure the stability and reliability of data transmission; use a signal connection line to connect the heating and cooling device to the central control unit to ensure accurate transmission of control signals; connect the mobile phone APP to the central control unit through a wireless network to achieve remote monitoring and management; open the mobile phone APP and enter the password or identification code connected to the central control unit; set the ideal temperature range in the tent and the working mode of the heating and cooling device in the APP; view the real-time temperature data in the tent through the APP and adjust the temperature settings as needed;

[0090] For details, please refer to Figure 1-Figure 2 , the central control unit includes a microprocessor, a memory and a communication interface;

[0091] In this embodiment: the microprocessor is the brain of the central control unit and is responsible for performing all calculations and logical operations; it processes data according to program instructions in the memory and controls other parts of the system; in the temperature monitoring system, the microprocessor processes the data of the temperature sensor, performs temperature calculations, and responds according to preset logic or instructions from the user; the memory is used to store the operating instructions and data of the central control unit; it usually includes read-only memory (ROM) and random access memory (RAM); the ROM usually solidifies the system's startup program and basic instructions, while the RAM is used to temporarily store the running program and processed data; the communication interface is the channel for the central control unit to exchange data with other devices or systems; in the temperature sensor module, the communication interface can be implemented by wired (such as serial communication, Ethernet) or wireless (such as Wi-Fi, Bluetooth, ZigBee); the central control unit can receive data from the temperature sensor through the communication interface and send control commands or configuration information to the sensor;

[0092] For details, please refer to Figure 1-Figure 2 , the temperature sensor module includes a plurality of temperature sensors, and the temperature sensors are connected to the central control unit via an independent wireless transmission module;

[0093] In this embodiment: a plurality of temperature sensors are fixed at different positions in the tent, respectively, for monitoring the temperature conditions at different positions in the tent, and the temperature sensors are connected to the central control unit via independent wireless transmission modules;

[0094] For details, please refer to Figure 1-Figure 2 , the heating and cooling device comprises a heater and a cooler, and the heater and the cooler are respectively connected to the output signal of the central control unit;

[0095] In this embodiment: the heating and cooling device includes a heater and a cooler, the heater is used to increase the temperature in the tent, and the cooler is used to reduce the temperature in the tent, both of which are controlled by a central control unit, which continuously receives current temperature data from the temperature sensor and controls the operation of the heating and cooling device according to the temperature conditions;

[0096] For details, please refer to Figure 1-Figure 2 , the mobile phone APP has the functions of displaying the temperature in the tent in real time, setting temperature thresholds and controlling heating and cooling devices;

[0097] In this embodiment: the role of the mobile phone APP in the wireless transmission temperature intelligent adjustment system is to provide a user interface so that the user can monitor the temperature in the tent in real time, set the temperature threshold and remotely control the heating and cooling devices; the APP can display the real-time temperature in the current tent, usually in the form of numbers and charts, so that the user can see it at a glance; the user can set the ideal temperature range, that is, the temperature threshold, in the APP; when the temperature in the tent exceeds or falls below this threshold, the APP will issue a reminder; the user can send instructions to the central control unit through the APP to control the switching of the heating and cooling devices and adjust the temperature settings; the APP can store and display the historical data of the temperature in the tent, which is convenient for the user to review and analyze; when the temperature in the tent exceeds the threshold set by the user, the APP can remind the user by notification, sound or vibration; the user can configure system parameters in the APP, such as language selection, unit conversion, network settings, etc.; the APP allows the user to set the temperature adjustment mode according to personal preferences, such as sleep mode, daytime mode, etc.; the APP may include a fault detection function that can identify problems in the system and provide corresponding prompts or solutions;

[0098] For details, please refer to Figure 1-Figure 2 , the wireless transmission module is a Bluetooth module, which is used to realize wireless communication between the central control unit and the temperature sensor module, the heating and cooling device;

[0099] In this embodiment: the wireless transmission module is a Bluetooth module, which is used to realize wireless communication between the central control unit and the temperature sensor module, the heating and cooling device;

[0100] For details, please refer to Figure 1-Figure 2 , the central control unit has the function of automatically adjusting the temperature, humidity and light in the tent;

[0101] In this embodiment: the central control unit has the function of automatically adjusting the temperature, humidity and light in the tent, and the user sets the temperature, humidity and light preferences through the central control unit; each control unit (TCU, HCU, LCU) senses the current environmental state through sensors and sends data to the central control unit; the central control unit analyzes the data and determines whether the environmental parameters need to be adjusted; when the environmental parameters deviate from the preset range, the central control unit sends instructions to the corresponding control units; the temperature control unit adjusts the heating or cooling equipment, the humidity control unit adjusts the humidification or dehumidification equipment, and the light control unit changes the light mode or intensity; during the adjustment process, each control unit continuously feeds back the operation effect to the central control unit to ensure that the environmental parameters reach and maintain the ideal state; the central control unit also optimizes energy use to ensure that the operation is both energy-saving and environmentally friendly;

[0102] For details, please refer to Figure 1-Figure 2, the system also includes a battery pack, which provides power for the central control unit, the temperature sensor module, the heating and cooling device, the mobile phone APP and the humidity sensor module, and has a long battery life;

[0103] In this embodiment: the battery pack provides power for the central control unit, the temperature sensor module, the heating and cooling device, the mobile phone APP and the humidity sensor module; the temperature sensor module and the humidity sensor module monitor the ambient temperature and humidity in real time and send the data to the central control unit; the central control unit analyzes the sensor data and decides whether to adjust the environmental parameters according to the temperature preference and humidity requirements set by the user; the heating and cooling device adjusts the temperature in the tent according to the instructions of the central control unit; the central control unit sends the system status and real-time data to the mobile phone APP through wireless communication, so that the user can understand the system operation status and environmental parameters in time; the whole system achieves long-term endurance when the battery pack provides power, ensuring a stable and comfortable environment in the tent;

[0104] For details, please refer to Figure 1-Figure 2 , the wireless transmission temperature intelligent adjustment system in the tent also includes a humidity sensor module, which is connected to the central control unit through the wireless transmission module and is used to monitor the humidity in the tent;

[0105] In this embodiment: the humidity sensor is the core of the module, which is used to measure the humidity in the environment. The wireless transmission module is responsible for sending the data measured by the humidity sensor to the central control unit; the central control unit is the decision center of the system, which receives and processes the data from the temperature and humidity sensor modules; the humidity sensor module continuously monitors the humidity level in the tent; the humidity data is sent to the central control unit in the form of a wireless radio frequency (RF) signal through the wireless transmission module; the central control unit receives the humidity data and compares it with the set humidity preference; if the humidity exceeds the preset range, the central control unit sends an instruction to the heating or cooling device to make corresponding adjustments; the system continuously monitors the humidity and cyclically executes the above steps to keep the humidity in the tent stable;

[0106] The working principle and use process of the present invention are as follows: when the present solution is used, the user enters the tent and sets the ideal temperature range through the user interface of the mobile phone APP; the temperature sensor starts to work and continuously monitors the ambient temperature, and transmits the data to the central control unit through the wireless module; the central control unit compares the real-time temperature data with the temperature range set by the user, and makes corresponding adjustments; if the temperature exceeds the range, the control unit will activate the corresponding heating or cooling device until the temperature returns to the set range; the control unit regularly analyzes the temperature data to optimize the energy utilization efficiency, and informs the user of the current temperature status and energy consumption through the user interface; by using the present solution, the temperature, humidity and other conditions in the tent are controlled by wireless intelligent control, and the temperature in the tent is adjusted in time, even in hot summer and cold winter, the temperature in the tent is suitable for people to live and move around, and it is controlled by the mobile phone APP, and the operation is simple and convenient;

[0107] In this embodiment, the wireless transmission temperature intelligent adjustment system in the tent is characterized by: receiving new environmental data in real time and predicting future temperature and humidity, and iteratively optimizing the imitation learning model according to user feedback and system performance data. The specific process is as follows;

[0108] Step 1: Data collection;

[0109] Collect real-time data using multiple temperature and humidity sensors inside the tent;

[0110] Step 2: Gated recurrent unit prediction;

[0111] The gated recurrent unit is selected as the machine learning model for time series prediction. The trained model is integrated into the central control unit so that it can receive sensor data in real time and predict future environmental changes. The gated recurrent unit is a popular recurrent neural network structure for processing time series data. GRU controls the information flow through two main gating mechanisms: update gate and reset gate. The specific formula is as follows.

[0112] Update Gate:

[0113] z t =σ(W z ·x t +U z ·h t-1 +b z )

[0114] Among them, z t represents the update gate at time step t, σ is the sigmoid function, W z represents the weight matrix of the update gate, x t represents the input vector at the current time step t, U z represents the weight matrix of the update gate, ht-1 represents the hidden state vector of the previous time step t-1, b z represents the bias vector of the update gate;

[0115] Reset the gate:

[0116] r t =σ(W r ·x t +U r ·h t-1 +b r )

[0117] Among them, r t represents the output vector of the reset gate, σ is the sigmoid activation function, and W r represents the weight matrix of the reset gate, x t represents the input vector at the current time step t, h t-1 represents the hidden state vector at the previous time step t-1, U r represents the weight matrix of the reset gate, b r represents the bias vector for the reset gate;

[0118] Candidate hidden states;

[0119]

[0120] represents the candidate hidden state vector, which is the candidate state of the current time step t and contains new information. Tanh represents the hyperbolic tangent activation function. W h Represents the input x for the current time step t t The weight matrix, h t-1 represents the hidden state vector at the previous time step t-1, U h Indicates the previous hidden state h t-1 The weight matrix, r t represents the output vector of the reset gate, ⊙ represents element-by-element multiplication, b h represents the bias vector;

[0121] Final hidden status update:

[0122]

[0123] Among them, h t represents the hidden state vector at the current time step t, z t Represents the output vector of the update gate, 1-z t represents the inverted output of the update gate, h t-1 represents the hidden state vector at the previous time step t-1, represents the candidate hidden state vector at the current time step t;

[0124] Step 3: Imitation learning;

[0125] Collect operational data from experts or experienced users when using the temperature control system in the tent, including how they adjust the temperature settings according to different environmental conditions; this data will serve as the basis for training the imitation learning model; behavioral cloning, to imitate the decision-making process of experts. The behavior cloning learning process is as follows;

[0126] a t =π θ (s t )

[0127] Among them, strategy π θ is a neural network, s t represents the state at time step t; a t represents the action selected by the expert at time step t;

[0128]

[0129] Among them, L(θ) is the loss function value under parameter θ, θ represents the parameter of the policy network, and a t Be an expert in status t The next action, π θ (s t ) is the policy model in state s t The predicted action is T, and T is the total number of demonstration data;

[0130] In order for the policy model to predict the expert's actions as accurately as possible, the optimization goal is set to minimize the above loss function:

[0131]

[0132] Among them, θ * Represents the optimal model parameters obtained after optimization; Represents the process of finding the parameter θ so that the loss function L(θ) reaches the minimum value;

[0133] Step 4: Preference adaptation;

[0134] By analyzing the user's behavior and preference settings in the APP, the algorithm automatically learns and presets the temperature and humidity range that the user may like;

[0135] P={p1,p2,...,p n}

[0136] p i =(t i ,h i )

[0137] Among them, P represents the user preference set, n represents the total number of data points, and p i represents the i-th user's response to temperature t i and humidity i preferences;

[0138] C={c1,c2,...,c k}

[0139] c j =(t′ j ,h′ j )

[0140] Among them, C represents the preference center, c k represents the kth preference center, c j Represents the temperature t′ of the jth cluster center j and humidity h′ j ;

[0141] The goal of clustering is to minimize the sum of the squared distances of all points to their nearest cluster center, that is, to minimize the objective function:

[0142]

[0143] Where J represents the objective function, which is the sum of the square distances of all points to their nearest cluster centers; n represents the total number of data points; k represents the total number of cluster centers; p i represents the position vector of the i-th data point; c j represents the position vector of the jth cluster center; w ij Represents an indicator variable. If the data point p i belongs to the jth cluster center, then w ij =1; otherwise w ij =0;||p i -c j || 2 Represents data point p i To cluster center c j The square of the Euclidean distance;

[0144] The process of cluster analysis is as follows:

[0145] Step 1: Randomly select k user preferences as the initial cluster center C;

[0146] Step 2: For each user preference p i , find the nearest cluster center c j , and update the indicator variable w ij :

[0147]

[0148] Among them, wij represents the indicator variable, representing the data point p i Whether to assign to the jth cluster center, if the data point p i belongs to the jth cluster center, then w ij =1, otherwise w ij =0;argmin j′ ||p i -c j′ || means to find the value such that ||p i -c j′ ||The smallest cluster center index j′, i.e. p i Which cluster center is closest to; c j′ represents the most recent cluster center after update, j′ represents the smallest cluster center index, otherwise represents other cases, w ij =0;

[0149] Step 3: Recalculate the center of each cluster to make it the mean of all points in the cluster:

[0150]

[0151] Among them, c j represents the coordinates of the jth cluster center; w ij represents the indicator variable, representing the data point p i Whether to assign to the jth cluster center, if the data point p i belongs to the jth cluster center, then w ij =1, otherwise w ij =0; p i represents the coordinates of the i-th data point; n represents the total number of data points;

[0152] Step 4: Repeat the assignment and update steps until the cluster center no longer changes significantly or reaches the preset number of iterations.

[0153] Numerical case analysis:

[0154] Obtain training data through collection;

[0155] Time: 08:00, 12:00; 18:00; 23:00;

[0156] Temperature in the tent (℃): 22; 28; 25; 20;

[0157] Temperature outside the tent (℃): 26; 35; 22; 18;

[0158] Humidity (%): 80; 50; 60; 70;

[0159] Actions: Cooling; Cooling; Heating; Heating;

[0160] Once the model is trained, it will be deployed to the temperature control system in the tent to predict and execute regulation strategies in real time;

[0161] The actual test results are:

[0162] Time: 09:00, 14:00, 20:00, 01:00

[0163] Temperature in the tent (℃): 24; 30; 23; 18;

[0164] Temperature outside the tent (℃): 30; 38; 20; 16;

[0165] Humidity (%): 75; 45; 65; 80;

[0166] Predicted actions: Cool down; Cool down; Heat up; Heat up;

[0167] Actual actions: cooling; cooling; heating; heating;

[0168] The model was able to correctly predict all regulatory actions, showing high accuracy;

[0169] User ID: 1; 2; 3; 4; 5;

[0170] Temperature preference (℃): 22; 24; 25; 22; 23;

[0171] Humidity preference (%): 45; 50; 60; 55; 50;

[0172] The initial cluster centers select the preferences of user 1 and user 3;

[0173] Assignment step: Calculate the Euclidean distance between each user's preference and the two centers, and assign them to the nearest center. User 1: (22,45)-(22,45)=0; (22,45)-(25,60)=16.4→assigned to c1; User 3: (25,60)-(22,45)=16.4; (25,60)-(25,60)=0→assigned to c2; Update step: Recalculate the cluster center.

[0174] c1==(23,48.33)

[0175] c2=(23.5,57.5)

[0176] The assignment and update steps are repeated until the change in cluster centers is less than a preset threshold or the maximum number of iterations is reached.

[0177] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A wireless transmission temperature intelligent adjustment system in a tent, characterized in that: include: Central control unit; A temperature sensor module, wherein the temperature sensor module is connected to the central control unit via a wireless transmission module; a heating and cooling device, the heating and cooling device being in signal connection with the central control unit; and A mobile phone APP is connected to the central control unit by signal.

2. The wireless transmission temperature intelligent adjustment system in a tent according to claim 1, characterized in that: The central control unit includes a microprocessor, a memory and a communication interface.

3. The wireless transmission temperature intelligent adjustment system in a tent according to claim 2, characterized in that: The temperature sensor module includes a plurality of temperature sensors, and the temperature sensors are connected to the central control unit via an independent wireless transmission module.

4. The wireless transmission temperature intelligent adjustment system in a tent according to claim 3, characterized in that: The heating and cooling device comprises a heater and a cooler, and the heater and the cooler are respectively connected to the output signal of the central control unit.

5. The wireless transmission temperature intelligent adjustment system in a tent according to claim 4, characterized in that: The mobile phone APP has the functions of displaying the temperature inside the tent in real time, setting temperature thresholds and controlling the heating and cooling devices.

6. The wireless transmission temperature intelligent adjustment system in a tent according to claim 5, characterized in that: The wireless transmission module is a Bluetooth module, which is used to realize wireless communication between the central control unit and the temperature sensor module, and the heating and cooling device.

7. The wireless transmission temperature intelligent adjustment system in a tent according to claim 6, characterized in that: The central control unit has the function of automatically adjusting the temperature, humidity and light in the tent.

8. The wireless transmission temperature intelligent adjustment system in a tent according to claim 7, characterized in that: The system also includes a battery pack that provides power to the central control unit, temperature sensor module, heating and cooling device, mobile phone APP and humidity sensor module, and has a long battery life.

9. The wireless transmission temperature intelligent adjustment system in a tent according to claim 8, characterized in that: The wireless transmission temperature intelligent adjustment system in the tent also includes a humidity sensor module, which is connected to the central control unit via the wireless transmission module and is used to monitor the humidity in the tent.

10. A method for intelligently adjusting temperature in a tent by wireless transmission, using a system for intelligently adjusting temperature in a tent by wireless transmission as claimed in any one of claims 1 to 9, characterized in that: The steps include: S1. When the user enters the tent, the user sets the ideal temperature range through the user interface of the mobile phone APP; S2, the temperature sensor starts working and continuously monitors the ambient temperature, and transmits the data to the central control unit through the wireless module; S3, the central control unit compares the real-time temperature data with the temperature range set by the user and makes corresponding adjustments; S4. If the temperature is out of range, the control unit will activate the corresponding heating or cooling device until the temperature returns to the set range; S5. The control unit regularly analyzes the temperature data to optimize energy efficiency and informs the user of the current temperature status and energy consumption through the user interface.

11. The method for intelligently adjusting temperature in a tent by wireless transmission according to claim 1, characterized in that: Receive new environmental data in real time and make predictions about future temperature and humidity. It also iteratively optimizes the imitation learning model based on user feedback and system performance data. The specific process is as follows: Step 1: Data collection; Collect real-time data using multiple temperature and humidity sensors inside the tent; Step 2: Gated recurrent unit prediction; The gated recurrent unit (GRU) is selected as the machine learning model for time series prediction. The trained model is integrated into the central control unit so that it can receive sensor data in real time and predict future environmental changes. The gated recurrent unit is a popular recurrent neural network structure for processing time series data. The GRU controls the information flow through two main gating mechanisms: update gate and reset gate. The specific formula is as follows: Update Gate: z t =σ(W z ·x t +U z ·h t-1 +b z ) Among them, z t represents the update gate at time step t, σ is the sigmoid function, W z represents the weight matrix of the update gate, x t represents the input vector at the current time step t, U z represents the weight matrix of the update gate, h t-1 represents the hidden state vector of the previous time step t-1, b z represents the bias vector of the update gate; Reset the gate: r t =σ(W r ·x t +U r ·h t-1 +b r ) Among them, r t represents the output vector of the reset gate, σ is the sigmoid activation function, and W r represents the weight matrix of the reset gate, x t represents the input vector at the current time step t, h t-1 represents the hidden state vector at the previous time step t-1, U r represents the weight matrix of the reset gate, b r represents the bias vector for the reset gate; Candidate hidden states; represents the candidate hidden state vector, which is the candidate state of the current time step t and contains new information. Tanh represents the hyperbolic tangent activation function. W h Represents the input x for the current time step t t The weight matrix, h t-1 represents the hidden state vector at the previous time step t-1, U h Indicates the previous hidden state h t-1 The weight matrix, r t represents the output vector of the reset gate, ⊙ represents element-by-element multiplication, b h represents the bias vector; Final hidden status update: Among them, h t represents the hidden state vector at the current time step t, z t Represents the output vector of the update gate, 1-z t represents the inverted output of the update gate, h t-1 represents the hidden state vector at the previous time step t-1, represents the candidate hidden state vector at the current time step t; Step 3: Imitation learning; Collect operational data from experts or experienced users when using the temperature control system in the tent, including how they adjust the temperature settings according to different environmental conditions; this data will serve as the basis for training the imitation learning model; behavioral cloning, to imitate the decision-making process of experts. The behavior cloning learning process is as follows; a t =π θ (s t ) Among them, strategy π θ is a neural network, s t represents the state at time step t; a t represents the action selected by the expert at time step t; Among them, L(θ) is the loss function value under parameter θ, θ represents the parameter of the policy network, and a t Be an expert in status t The following action, π θ (s t ) is the policy model in state s t The predicted action is T, and T is the total number of demonstration data; In order for the policy model to predict the expert's actions as accurately as possible, the optimization goal is set to minimize the above loss function: Among them, θ* represents the optimal model parameters obtained after optimization; Represents the process of finding the parameter θ so that the loss function Reach a minimum value; Step 4: Preference adaptation; By analyzing the user's behavior and preference settings in the APP, the algorithm automatically learns and presets the temperature and humidity range that the user may like; P={p1,p2,...,p n } p i =(t i ,h i ) Among them, P represents the user preference set, n represents the total number of data points, and p i represents the i-th user's response to temperature t i and humidity i preferences; C={c1,c2,...,c k } c j =(t′ j ,h′ j ) Among them, C represents the preference center, c k represents the kth preference center, c j Represents the temperature t′ of the jth cluster center j and humidity h′ j ; The goal of clustering is to minimize the sum of the squared distances of all points to their nearest cluster center, that is, to minimize the objective function: Where J represents the objective function, which is the sum of the square distances of all points to their nearest cluster centers; n represents the total number of data points; k represents the total number of cluster centers; p i represents the position vector of the i-th data point; c j represents the position vector of the jth cluster center; w ij Represents an indicator variable. If the data point p i belongs to the jth cluster center, then w ij =1; otherwise w ij =0;||p i -c j || 2 Represents data point p i To cluster center c j The square of the Euclidean distance; The process of cluster analysis is as follows: Step 1: Randomly select k user preferences as the initial cluster center C; Step 2: For each user preference p i , find the nearest cluster center c j , and update the indicator variable w ij : Among them, w ij represents the indicator variable, representing the data point p i Whether to assign to the jth cluster center, if the data point p i belongs to the jth cluster center, then w ij =1, otherwise w ij =0;c j′ represents the most recent cluster center after update, j′ represents the smallest cluster center index, argmin j′ ||p i -c j′ || means to find the value such that ||p i -c j′ ||The smallest cluster center index j′, i.e. p i Which cluster center is closest to; otherwise means in other cases, w ij =0; Step 3: Recalculate the center of each cluster to make it the mean of all points in the cluster: Among them, c j represents the coordinates of the jth cluster center; w ij represents the indicator variable, representing the data point p i Whether to assign to the jth cluster center, if the data point p i belongs to the jth cluster center, then w ij =1, otherwise w ij =0; p i represents the coordinates of the i-th data point; n represents the total number of data points; Step 4: Repeat the assignment and update steps until the cluster center no longer changes significantly or reaches the preset number of iterations.

Images