A temperature controller and control method for a smart toilet

Abstract

This invention discloses a temperature controller and control method for a smart toilet, including temperature control of the smart toilet based on a temperature control system. The temperature control system includes a control module, a temperature module, and a temperature acquisition module. The control module includes an information transmission module, an information input terminal, and a controller. The temperature acquisition module and the information transmission module are respectively connected to the controller. This invention utilizes a backpropagation algorithm of a neural network and sets K... G w p '(n)(k), w i '(n)(k) and w d '(n)(k) realizes the function of the neural network to perform self-learning and temperature control at the same time, and helps to ensure the convergence of the entire neural network self-learning process. Through the self-learning ability of the neural network, it can fit the temperature control system of the refrigeration / heating element well, achieve good temperature control effect, and has strong adaptability and good stability.

Description

Technical Field

[0001] This invention belongs to the field of temperature control for smart toilets, and relates to a temperature controller and control method for a smart toilet. Background Technology

[0002] For industries with stringent temperature requirements, such as metallurgy and smart homes, temperature control technology is particularly crucial. The PID algorithm is commonly used for temperature control, catering to different scenarios with varying temperature control precision and environmental conditions. While the PID algorithm offers good fit for linear systems, it performs poorly on nonlinear systems, making it difficult to achieve high-precision control.

[0003] The smart toilet model uses cooling / heating elements (semiconductor chips) to achieve cooling or heating. Due to the nonlinear electrical characteristics and discrete spatial distribution of the cooling / heating elements, the temperature control system of the cooling / heating elements in the smart toilet model becomes a typical nonlinear system, and it is difficult to achieve good temperature control effect using traditional PID algorithms. Summary of the Invention

[0004] In order to overcome the shortcomings of the prior art, the present invention provides a temperature control method for a smart toilet.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: a temperature controller for a smart toilet, comprising a temperature control system for controlling the temperature of the smart toilet, the temperature control system comprising a control module, a temperature module, and a temperature acquisition module, the control module comprising an information transmission module, an information input terminal, and a controller, the temperature acquisition module and the information transmission module being connected to the controller respectively, comprising the following steps:

[0006] Step 1: Input the target temperature TS;

[0007] The information transmission module acquires the target temperature data from the information input terminal and transmits the set target temperature TS to the controller.

[0008] Step 2: Obtain the actual temperature T R (n)(k);

[0009] Step 3: Determine the basic parameters;

[0010] Step 4: The controller acquires the target temperature T S and actual temperature T R (n)(k) is used to obtain the duty cycle of the PWM wave of a certain k path in a certain n-time control process;

[0011] Step 5: The controller outputs a PWM wave to the temperature module to make the temperature at each measuring point reach the target temperature;

[0012] Step 6: After each control process is completed, the information transmission module reads the data from the information input terminal to obtain the user's target temperature setting. If there is updated target temperature data, the information transmission module will update the target temperature data and transmit it to the controller, then execute Step 1. Otherwise, proceed to the next step.

[0013] Furthermore, in step 2, during a single control process, a temperature acquisition module collects the temperature at the measuring point where the temperature module is located, forming a path of actual temperature data T that is transmitted to the controller. R (1)(1), the temperature acquisition module at the kth location acquires the temperature of the area where the kth temperature acquisition module is located and forms the actual temperature data T that is transmitted to the controller via k channels. R (1)(k), during the nth control process, a temperature acquisition module collects the temperature of the area where the temperature acquisition module is located and forms a path of actual temperature data T that is transmitted to the controller. R (n)(1), the temperature acquisition module at the k-th location acquires the temperature of the area where the k-th temperature acquisition module is located and forms the actual temperature data T transmitted to the controller via k channels. R (n)(k).

[0014] Furthermore, the value of k is the same as the number of temperature acquisition modules and the number of temperature modules.

[0015] Furthermore, step 3 includes the following steps:

[0016] Step 3.1: Determine the weight parameters for each PID controller;

[0017] w p (n+1)(k)=w p (n)(k)+v p u(n)(k)e(n)(k)x1(n)(k);

[0018] w i (n+1)(k)=w i (n)(k)+v i u(n)(k)e(n)(k)x2(n)(k);

[0019] w i (n+1)(k)=w i (n)(k)+v i u(n)(k)e(n)(k)x2(n)(k);

[0020] Where n represents the number of control processes required to reach the target temperature, and k represents the measurement point number of the smart toilet.

[0021] w p(n)(k) represents the weight parameter of the proportional term of the PID controller in the k-th neuron during the n-th control process, w p (n+1)(k) represents the weight parameter of the proportional term of the PID controller in the (n+1)th neuron during the control process, v p x1(n)(k) is the learning rate of the proportional term in the neuron's PID, and x1(n)(k) is the proportional term in the PID when the neuron's input is 1.

[0022] w i (n)(k) represents the weight parameters of the PID integral term of the k-th neuron in the nth control process, w i (n+1)(k) represents the weight parameter of the PID integral term of the k-th neuron in the (n+1)-th control process, v i x2(n)(k) is the learning rate of the integral term in the PID of the neuron, and x2(n)(k) is the integral term in the PID when the neuron inputs 2.

[0023] w d (n)(k) represents the weight parameters of the PID differential term of the k-th neuron in a certain nth control process, w d (n+1)(k) represents the weight parameter of the PID differential term of the k-th neuron in a certain (n+1)th control process, v d x3(n)(k) is the learning rate of the differential term in the PID of the neuron, and x3(n)(k) is the differential term in the PID when the neuron inputs 3.

[0024] In the formula, e(n)(k) represents the actual temperature T of a certain k-channel during a certain n-times control process. R (n)(k) and the set target temperature T S The error between them is e(n-1)(k), which is the error between the actual temperature of the kth channel and the set target temperature in the first n-1 control process; e(n-2)(k), which is the error between the actual temperature of the kth channel and the set target temperature in the first n-2 control process; and u(n)(k), which is the duty cycle of the PWM wave of a certain kth channel in a certain n control process.

[0025] Step 3.2: Determine the duty cycle increment;

[0026] The duty cycle increment Δu(n)(k) is the output of each of the n channels in the nth control process:

[0027] △u(n)(k)=KG(w p '(n)(k)x1(n)(k)+wi'(n)(k)x2(n)(k)+wd'(n)(k)x3(n)(k));

[0028] In the formula, KG represents the total learning rate of the neuron;

[0029] Step 3.3: Determine the duty cycle of the PWM wave;

[0030] Let the duty cycle be u(n)(k).

[0031] u(n)(k)=△u(n)(k)+△u(n-1)(k)+...+△u(1)(1)+u a ;

[0032] The formula ua represents the initial value for setting the duty cycle of the PWM wave;

[0033] Furthermore, in step 3.1, x1(n)(k) = e(n)(k) - e(n-1)(k).

[0034] Furthermore, in step 3.1, x2(n)(k) = e(n)(k) + e(n-1)(k) + e(n-2)(k).

[0035] Furthermore, in step 3.1

[0036] x3(n)(k)=e(n)(k)-2×e(n-1)(k)+e(n-2)(k).

[0037] Furthermore, vp, vi, and vd are set values.

[0038] Furthermore, KG is a set value.

[0039] Furthermore, the information transmission module is configured as a WIFI module for data transmission between the controller and the information input terminal. The information input terminal includes buttons and / or a remote control and / or a mobile APP. The information transmission module acquires the temperature data of the information input terminal.

[0040] A temperature control system for an intelligent toilet includes an intelligent toilet, a control module, a temperature module, and a temperature acquisition module. The control module includes an information transmission module, an information input terminal, and a controller. The temperature acquisition module and the information transmission module are respectively connected to the controller.

[0041] Furthermore, the information transmission module is configured as a WIFI module for data transmission between the controller and the information input terminal. The information input terminal includes buttons and / or a remote control and / or a mobile APP. The information transmission module acquires the temperature data from the information input terminal.

[0042] Furthermore, the temperature module is set as a semiconductor chip, and the temperature module is installed in the smart toilet.

[0043] Furthermore, several temperature modules are set up, and these temperature modules are distributed in the toilet seat of the smart toilet.

[0044] Furthermore, the temperature acquisition module and the temperature module should be configured to correspond at least one-to-one.

[0045] Furthermore, a temperature acquisition module collects the temperature at the measuring point where the temperature acquisition module is located, forming a path of actual temperature data that is transmitted to the control module.

[0046] A temperature controller for a smart toilet, the temperature controller comprising:

[0047] The target temperature setting unit sets the target temperature TS.

[0048] The temperature acquisition unit is used to obtain the actual temperature T at the measuring point of the smart toilet. R (n)(k);

[0049] The parameter setting unit is used to determine the weight parameters of each PID, the duty cycle increment, and the duty cycle of the PWM wave.

[0050] The operations department obtains the target temperature T. S and actual temperature T R (n)(k) is used to obtain the duty cycle of the PWM wave of a certain k path in a certain n-time control process;

[0051] The output section is used to output PWM waves to the temperature module so that the temperature at each measuring point reaches the target temperature.

[0052] The data confirmation unit is used to receive updated target temperature data.

[0053] Further, determine the weight parameters for each PID controller;

[0054] w p (n+1)(k)=w p (n)(k)+v p u(n)(k)e(n)(k)x1(n)(k);

[0055] w i (n+1)(k)=w i (n)(k)+v i u(n)(k)e(n)(k)x2(n)(k);

[0056] w i (n+1)(k)=w i (n)(k)+v i u(n)(k)e(n)(k)x2(n)(k);

[0057] Where n represents the number of control processes required to reach the target temperature, k represents the measurement point number of the smart toilet, and w p (n)(k) represents the weight parameter of the proportional term of the PID controller in the k-th neuron during the n-th control process, w p(n+1)(k) represents the weight parameter of the proportional term of the PID of the k-th neuron in the (n+1)-th control process, vp represents the learning rate of the proportional term of the PID of the neuron, and x1(n)(k) represents the proportional term in the PID when the neuron inputs 1.

[0058] w i (n)(k) represents the weight parameters of the PID integral term of the k-th neuron in the nth control process, w i (n+1)(k) represents the weight parameter of the PID integral term of the k-th neuron in the (n+1)-th control process, v i x2(n)(k) is the learning rate of the integral term in the PID of the neuron, and x2(n)(k) is the integral term in the PID when the neuron inputs 2.

[0059] w d (n)(k) represents the weight parameters of the PID differential term of the k-th neuron in a certain nth control process, w d (n+1)(k) represents the weight parameter of the PID differential term of the k-th neuron in a certain (n+1)th control process, v d x3(n)(k) is the learning rate of the differential term in the PID of the neuron, and x3(n)(k) is the differential term in the PID when the neuron inputs 3.

[0060] In the formula, e(n)(k) represents the actual temperature T of a certain k-channel during a certain n-times control process. R (n)(k) and the set target temperature T S The error between them is given by e(n-1)(k), which is the error between the actual temperature of the kth channel and the set target temperature during the first n-1 control processes, e(n-2)(k), which is the error between the actual temperature of the kth channel and the set target temperature during the first n-2 control processes, and u(n)(k), which is the duty cycle of the PWM wave of a certain kth channel during a certain nth control process.

[0061] Furthermore, determine the duty cycle increment;

[0062] The duty cycle increment Δu(n)(k) is the output of each of the n channels in the nth control process:

[0063] △u(n)(k)=KG(w p '(n)(k)x1(n)(k)+wi'(n)(k)x2(n)(k)+wd'(n)(k)x3(n)(k));

[0064] In the formula, KG represents the total learning rate of the neuron.

[0065] Furthermore, determine the duty cycle of the PWM wave;

[0066] Let the duty cycle be u(n)(k).

[0067] u(n)(k)=△u(n)(k)+△u(n-1)(k)+...+△u(1)(1)+u a ;

[0068] In the formula, ua is the initial value set for the duty cycle of the PWM wave;

[0069] Furthermore, x1(n)(k) = e(n)(k) - e(n-1)(k).

[0070] Furthermore, x2(n)(k) = e(n)(k) + e(n-1)(k) + e(n-2)(k).

[0071] Furthermore, x3(n)(k) = e(n)(k) - 2 × e(n-1)(k) + e(n-2)(k).

[0072] Furthermore, vp, vi, and vd are set values.

[0073] Furthermore, KG is a set value.

[0074] In summary, the advantages of this invention are:

[0075] This invention utilizes the backpropagation algorithm of a neural network and sets KG and w p '(n)(k), w i '(n)(k) and w d '(n)(k) realizes the function of the neural network to perform self-learning and temperature control at the same time, and helps to ensure the convergence of the entire neural network self-learning process. Through the self-learning ability of the neural network, it can fit the temperature control system of the refrigeration / heating element well, achieve good temperature control effect, and has strong adaptability and good stability. Attached Figure Description

[0076] Figure 1 This is a flowchart of the present invention. Detailed Implementation

[0077] The following specific examples illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that, unless otherwise specified, the following embodiments and features described therein can be combined with each other.

[0078] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. Therefore, the drawings only show the components related to the present invention and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0079] In this embodiment of the invention, all directional indicators (such as up, down, left, right, front, back, lateral, longitudinal, etc.) are only used to explain the relative positional relationship and movement of each component in a specific posture. If the specific posture changes, the directional indicator will also change accordingly.

[0080] Due to installation errors and other reasons, the parallel relationship referred to in the embodiments of the present invention may actually be an approximate parallel relationship, and the perpendicular relationship may actually be an approximate perpendicular relationship.

[0081] Example 1:

[0082] like Figure 1 As shown, a temperature control system for an intelligent toilet includes an intelligent toilet, a control module, a temperature module, and a temperature acquisition module. The control module includes an information transmission module, an information input terminal, and a controller. The temperature acquisition module and the information transmission module are respectively connected to the controller.

[0083] In this embodiment, the information transmission module is set as a WIFI module for data transmission between the controller and the information input terminal. The information input terminal includes buttons and / or a remote control and / or a mobile APP. The information transmission module acquires the temperature data of the information input terminal.

[0084] In this embodiment, the temperature module is set as a semiconductor chip and is installed in the smart toilet, preferably in the toilet seat, to heat or cool the seat and achieve accurate temperature control.

[0085] In this embodiment, several temperature modules are evenly distributed on the toilet seat to ensure uniform heating or cooling. Temperature acquisition modules are located on the toilet seat and close to the temperature modules. Preferably, there is at least a one-to-one correspondence between the temperature acquisition modules and the temperature modules. Each temperature acquisition module collects temperature data from the area where the temperature module is located, i.e., the temperature of one measuring point forms a path of actual temperature data that is transmitted to the control module. Multiple measuring points form multiple data paths. In this embodiment, the multiple measuring points are labeled to form data paths 1 to k, where k is the measuring point number of the smart toilet.

[0086] This application also provides a temperature controller for a smart toilet, which controls the temperature of the smart toilet based on a temperature control system. The temperature control system includes a control module, a temperature module, and a temperature acquisition module. The control module includes an information transmission module, an information input terminal, and a controller. The temperature acquisition module and the information transmission module are respectively connected to the controller. The specific steps include:

[0087] Step 1: Input the target temperature TS;

[0088] The information transmission module acquires the target temperature data from the information input terminal and transmits the set target temperature TS to the controller.

[0089] Step 2: Obtain the actual temperature T R (n)(k);

[0090] During a single control process, a temperature acquisition module collects the temperature of a measuring point in the area where the temperature acquisition module is located. That is, the temperature of one measuring point forms a path of actual temperature data T that is transmitted to the controller. R (1)(1), the temperature acquisition module collects the temperature of the measuring point in the area where the k-th temperature module is located and forms the actual temperature data T that is transmitted to the controller via k channels. R (1)(k);

[0091] During the nth control process, a temperature acquisition module collects the temperature of the area where the temperature acquisition module is located, forming a line of actual temperature data T that is transmitted to the controller. R (n)(1), the temperature acquisition module at the k-th location acquires the temperature of the area where the k-th temperature acquisition module is located and forms the actual temperature data T transmitted to the controller via k channels. R (n)(k);

[0092] In this embodiment, k is the measurement point number of the smart toilet.

[0093] In this embodiment, n represents the number of control processes required for the actual temperature to reach the target temperature. After n control processes, the actual temperature at each measuring point reaches the set target temperature.

[0094] Step 3: Determine the basic parameters;

[0095] Step 3.1: Determine the weight parameters for each PID controller;

[0096] w p (n+1)(k)=w p (n)(k)+v p u(n)(k)e(n)(k)x1(n)(k); (1)

[0097] w i (n+1)(k)=w i (n)(k)+vi u(n)(k)e(n)(k)x2(n)(k); (2)

[0098] w d (n+1)(k)=w d (n)(k)+v d u(n)(k)e(n)(k)x3(n)(k); (3)

[0099] w in formula (1) p w is the weight parameter of the proportional term in the neuron's PID. p (n)(k) represents the weight parameter of the proportional term of the PID controller in the k-th neuron during the n-th control process, w p (n+1)(k) is the weight parameter of the proportional term of the PID of the k-th neuron in the (n+1)-th control process, vp is the learning rate of the proportional term of the PID of the neuron, x1(n)(k) is the proportional term in the PID when the neuron inputs 1, x1(n)(k)=e(n)(k)-e(n-1)(k);

[0100] w in formula (2) i w is the weight parameter of the integral term of the PID in the neuron. i (n)(k) represents the weight parameters of the PID integral term of the k-th neuron in the nth control process, w i (n+1)(k) is the weight parameter of the PID integral term of the k-th neuron in the (n+1)-th control process, vi is the learning rate of the PID integral term of the neuron, x2(n)(k) is the integral term in the PID when the neuron inputs 2, x2(n)(k)=e(n)(k)+e(n-1)(k)+e(n-2)(k);

[0101] w in formula (3) d w represents the weight parameters of the differential term in the neuron's PID. d (n)(k) represents the weight parameters of the PID differential term of the k-th neuron in a certain nth control process, w d (n+1)(k) is the weight parameter of the differential term of the PID of the k-th neuron in the (n+1)-th control process, vd is the learning rate of the differential term of the PID of the neuron, and x3(n)(k) is the differential term in the PID when the neuron inputs 3, x3(n)(k)=e(n)(k)-2×e(n-1)(k)+e(n-2)(k);

[0102] In formulas (1), (2), and (3), e(n)(k) represents the actual temperature T of a certain k-channel during a certain n-times control process. R (n)(k) and the set target temperature T S The error between them, e(n)(k)=T R (n)(k)-TS e(n-1)(k) represents the error between the actual temperature and the set target temperature of the k-th channel during the first n-1 control processes, and e(n-2)(k) represents the error between the actual temperature and the set target temperature of the k-th channel during the first n-2 control processes.

[0103] In formulas (1), (2) and (3), u(n)(k) is the duty cycle of the PWM wave of a certain k-channel during a certain n-time control process; in formulas (1), (2) and (3), vp, vi and vd are set values.

[0104] Step 3.2: Determine the duty cycle increment;

[0105] Duty cycle increment Δu(n)(k), Δu(n)(k) is the output of each of the n channels in the nth control process: Δu(n)(k) = KG(w p '(n)(k)x1(n)(k)+wi'(n)(k)x2(n)(k)+wd'(n)(k)x3(n)(k)); In the formula, KG is the total learning rate of the neuron, and KG is the set value.

[0106] w p '(n)(k) represents the weight percentage of the proportional term in the neuron's PID.

[0107] w i '(n)(k) represents the weight ratio of the PID integral term in the neuron.

[0108] w d '(n)(k) represents the weight ratio of the differential term in the neuron's PID.

[0109] Step 3.3: Determine the duty cycle of the PWM wave;

[0110] Using the backpropagation algorithm of the neural network, we obtain u(n)(k)=△u(n)(k)+△u(n-1)(k)+...+△u(1)(1)+u a ;

[0111] The formula ua represents the initial value for setting the duty cycle of the PWM wave.

[0112] The duty cycle of a PWM wave is the sum of the initial value and the duty cycle increment.

[0113] Step 4: The controller acquires the target temperature T S and actual temperature T R (n)(k), so u(n)(k) is the duty cycle of a certain k-channel PWM wave in a certain n-time control process.

[0114] The controller outputs a PWM wave. Under the same conditions, such as using the same materials, the direction of the PWM wave controls whether the temperature module is cooling or heating. The duty cycle of the PWM wave is proportional to the cooling or heating power of the temperature module, and the ratio is set according to the actual situation.

[0115] This embodiment acquires the actual temperature of k measurement points during a single control process and processes it in conjunction with the target temperature. Simultaneously, it acquires the actual temperature of k measurement points during n control processes and processes it in conjunction with the target temperature. The weight parameters of each PID controller on the k-channel are adjusted during the n control processes, and w is increased. p The functions '(n)(k), wi'(n)(k), and wd'(n)(k) help ensure the convergence of the entire neural network self-learning process, thereby enabling the controller to generate multiple PWM waves with a certain duty cycle to control the cooling / heating modules.

[0116] Step 5: The controller outputs a PWM wave to the temperature module so that the temperature at each measuring point reaches the target temperature.

[0117] Step 6: After each control process is completed, the information transmission module reads information once to obtain the user's target temperature setting. If there is updated target temperature data, i.e., the previously set target temperature is changed, the information transmission module will send the updated target temperature data to the controller and execute Step 1. Otherwise, execute the next step.

[0118] This embodiment utilizes the backpropagation algorithm of a neural network and sets KG and w p '(n)(k), wi'(n)(k), and wd'(n)(k) enable the neural network to perform self-learning and temperature control simultaneously, which helps to ensure the convergence of the entire neural network self-learning process. Through the self-learning capability of the neural network, the temperature control system of the refrigeration / heating element can be well fitted, achieving good temperature control effect, with strong adaptability and excellent stability.

[0119] This application also provides a temperature controller for a smart toilet, the temperature controller comprising:

[0120] The target temperature setting unit sets the target temperature TS.

[0121] The temperature acquisition unit is used to obtain the actual temperature T at the measuring point of the smart toilet. R (n)(k);

[0122] The parameter setting unit is used to determine the weight parameters of each PID, the duty cycle increment, and the duty cycle of the PWM wave.

[0123] The operations department obtains the target temperature T. S and actual temperature TR (n)(k) is used to obtain the duty cycle of the PWM wave of a certain k path in a certain n-time control process;

[0124] The output section is used to output PWM waves to the temperature module so that the temperature at each measuring point reaches the target temperature.

[0125] The data confirmation unit is used to receive updated target temperature data.

[0126] Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort should fall within the scope of protection of the present invention.

Claims

1. A temperature controller for an intelligent toilet, characterized in that: include The target temperature setting unit sets the target temperature. ; The temperature acquisition unit is used to obtain the actual temperature of the measuring points on the smart toilet. ; The parameter setting unit is used to determine the weight parameters of each PID, the duty cycle increment, and the duty cycle of the PWM wave. The operations department obtains the target temperature. and actual temperature The duty cycle of the PWM wave of a certain k-channel is obtained during a certain n-time control process; The output section is used to output PWM waves to the temperature module so that the temperature at each measuring point reaches the target temperature. The data confirmation unit is used to receive updated target temperature data; Determine the weight parameters for each PID controller; ； ； ； Where n represents the number of control processes required to reach the target temperature, and k represents the measurement point number of the smart toilet. For the nth control process, the weight parameter of the proportional term of the PID of the k-th neuron is given. For the (n+1)th control process, the weight parameter of the proportional term of the PID of the k-th neuron is given. The learning rate of the proportional term in the neuron's PID controller. When the neuron is input with 1, the proportional term in the PID; For the nth control process, the weight parameters of the PID integral term of the k-th neuron are... For the (n+1)th control process, the weight parameters of the PID integral term of the k-th neuron are... The learning rate is the integral term of the neuron's PID. When the neuron is input 2, the integral term in the PID; The weight parameters of the PID differential term of the k-th neuron in a certain n-fold control process are: The weight parameters of the PID differential term of the k-th neuron in a certain (n+1)th control process are... The learning rate of the differential term of the neuron's PID. The differential term in the PID when the neuron is input 3; in the formula For a certain k-channel actual temperature during a certain n-times control process and the set target temperature The error between them The error between the actual temperature and the set target temperature of the k-th channel during the first n-1 control processes is... This represents the error between the actual temperature and the set target temperature in the k-th control path during the first n-2 control processes. Let be the duty cycle of a certain k-channel PWM wave during a certain n-times control process; Determine the duty cycle increment: Duty cycle increment This represents the output of each of the n channels in the nth control process. The calculation formula is: ； in The total learning rate of the neuron; The weighting percentage of the proportional term in the neuron's PID. ； The weight ratio of the integral term of the PID in the neuron. ； The weight ratio of the differential term in the neuron's PID. ； Determine the duty cycle of the PWM wave; Duty cycle set to : ； in The initial value set for the duty cycle of the PWM wave; When the neuron receives a 1 input, the proportional term in the PID controller is as follows: ； When neuron inputs 2, the integral term in the PID is as follows: ； When the neuron receives input 3, the differential term in the PID is as follows: ； The , and Set value; The This is the set value.

2. A temperature control method for a smart toilet, characterized in that: The temperature of the smart toilet is controlled by a temperature control system, which includes a control module, a temperature module, and a temperature acquisition module. The control module includes an information transmission module, an information input terminal, and a controller. The temperature acquisition module and the information transmission module are connected to the controller. The information transmission module is configured as a Wi-Fi module for data transmission between the controller and the information input terminal. The information input terminal includes buttons and / or a remote control and / or a mobile app. The information transmission module acquires the temperature data from the information input terminal, including the following steps: Step 1: Enter the target temperature setting ; The information transmission module acquires the target temperature data from the information input terminal and transmits the set target temperature to the controller. ; Step 2: Obtain the actual temperature ; In step 2, during one control process, a temperature acquisition module collects the temperature at the measuring point where the temperature module is located, forming a stream of actual temperature data that is transmitted to the controller. The temperature acquisition module at point k collects the temperature of the area where the k-th temperature acquisition module is located, forming k channels of actual temperature data that are transmitted to the controller. During the nth control process, a temperature acquisition module collects the temperature of the area where the temperature acquisition module is located, forming a line of actual temperature data that is transmitted to the controller. The temperature acquisition module at point k collects the temperature of the area where the k-th temperature acquisition module is located, forming k channels of actual temperature data that are transmitted to the controller. ; Step 3: Determine the basic parameters; Step 3 includes the following steps: Step 3.1: Determine the weight parameters for each PID controller; ； ； ； Where n represents the number of control processes required to reach the target temperature, and k represents the measurement point number of the smart toilet. For the nth control process, the weight parameter of the proportional term of the PID of the k-th neuron is given. For the (n+1)th control process, the weight parameter of the proportional term of the PID of the k-th neuron is given. The learning rate of the proportional term in the neuron's PID controller. When the neuron is input with 1, the proportional term in the PID; For the nth control process, the weight parameters of the PID integral term of the k-th neuron are... For the (n+1)th control process, the weight parameters of the PID integral term of the k-th neuron are... The learning rate is the integral term of the neuron's PID. When the neuron is input 2, the integral term in the PID; The weight parameters of the PID differential term of the k-th neuron in a certain n-fold control process are: The weight parameters of the PID differential term of the k-th neuron in a certain (n+1)th control process are... The learning rate of the differential term of the neuron's PID. The differential term in the PID when the neuron is input 3; in the formula For a certain k-channel actual temperature during a certain n-times control process and the set target temperature The error between them The error between the actual temperature and the set target temperature of the k-th channel during the first n-1 control processes is... This represents the error between the actual temperature and the set target temperature in the k-th control path during the first n-2 control processes. Let be the duty cycle of a certain k-channel PWM wave during a certain n-times control process; Step 3.2: Determine the duty cycle increment; Duty cycle increment This represents the output of each of the n channels in the nth control process. The calculation formula is: ； in The total learning rate of the neuron; The weighting percentage of the proportional term in the neuron's PID. ； The weight ratio of the integral term of the PID in the neuron. ； The weight ratio of the differential term in the neuron's PID. ； Step 3.3: Determine the duty cycle of the PWM wave; Duty cycle The calculation formula is: ； in The initial value set for the duty cycle of the PWM wave; Step 4: The controller acquires the target temperature. and actual temperature The duty cycle of the PWM wave of a certain k-channel is obtained during a certain n-time control process; Step 5: The controller outputs a PWM wave to the temperature module to make the temperature at each measuring point reach the target temperature; Step 6: After each control process is completed, the information transmission module reads the data from the information input terminal to obtain the user's target temperature setting. If there is updated target temperature data, the information transmission module will update the target temperature data and transmit it to the controller, then execute Step 1. Otherwise, proceed to the next step. The duty cycle of the PWM wave is proportional to the cooling or heating power of the temperature module.

Images