Dryer temperature and humidity control system and method based on neural network

Abstract

The invention provides a dryer temperature and humidity control system and method based on a neural network, and the system comprises a sensing data collection unit, a sensing data processing unit, a heating resistor power collection unit, a BP neural network controller, and a PID controller. The input end of the sensing data acquisition unit is connected with a roller rotating speed sensor and a cooling fan rotating speed sensor, the output end of the sensing data acquisition unit is connected with the BP neural network controller through the sensing data processing unit, and the heating resistor power acquisition unit is connected with the BP neural network controller. The BP neural network controller is connected with the PID controller through the temperature adjusting unit and the humidity adjusting unit, the working principle is simple, a BP neural network algorithm is introduced for a multi-input multi-output time-varying nonlinear system of the grain dryer, a neural network model of the system is obtained through learning of a large amount of original data, and the temperature adjusting unit and the humidity adjusting unit are used for controlling the temperature adjusting unit and the humidity adjusting unit. And in combination with a traditional PID control algorithm, closed-loop control of the whole drying process is realized.

Description

Technical Field

[0001] The present application relates to the technical field of temperature and humidity control of dryers, and in particular to a temperature and humidity control system and method for dryers based on a neural network. Background Art

[0002] Dryers can be divided into industrial and civil types. Industrial dryers are also called drying equipment or dryers. Civil dryers are a type of washing machine, generally used to remove moisture from clothing and other textiles after washing and dehydration.

[0003] There are several modes of dryers, such as belt drying, drum drying, box drying, tower drying, etc. The heat sources include coal, electricity, gas, etc. The materials are dried in hot air flow and radiation processes. Hot air drum drying is a process in which the hot air flow moves from the tail to the front, fully contacts the materials, and fully utilizes the heat transfer through heat conduction, convection, and radiation. The heat energy is directly transferred to the materials, so that the moisture of the materials is continuously evaporated in the drum. The induced draft device at the inlet draws out a large amount of moisture and wet air flow to prevent secondary pollution caused by dust discharge. The material movement is promoted through internal spiral stirring, sweeping, and copying to complete the entire drying process. Countercurrent conduction dehumidification avoids reducing repeated drying procedures.

[0004] Artificial neural network is a mathematical model that uses a structure similar to the synaptic connection of the brain to process information. In engineering and academia, it is often referred to as a neural network or a quasi-neural network. A neural network is a computational model consisting of a large number of nodes (or neurons) and connections between them. Each node represents a specific output function, called an activation function. The connection between each two nodes represents a weighted value for the signal passing through the connection, called a weight, which is equivalent to the memory of the artificial neural network. The output of the network varies depending on the connection mode, weight value and activation function of the network. The network itself is usually an approximation of a certain algorithm or function in nature, or it may be an expression of a logical strategy. At present, small and medium-sized drum grain dryers use the parameters that mainly affect the temperature and humidity in the oven, such as the dryer drum speed, exhaust fan speed, and heating heat source power, as the input layer variables of the entire system, and the real-time temperature and humidity parameters in the oven tested by the sensor as the output layer variables to build a multi-input, multi-output system. Because the environment inside the dryer oven has obvious nonlinear characteristics, and there is a certain coupling between the multi-variable inputs, the entire system is also a time-varying system. It is difficult to effectively control this complex environmental system using a single traditional PID control strategy. Therefore, it is necessary to design a dryer temperature and humidity control system based on a neural network. Summary of the invention

[0005] The present application provides a temperature and humidity control system and method for a dryer based on a neural network to solve the problem that it is difficult to effectively control this complex environmental system using a single traditional PID control strategy. The neural network model of the system is obtained by learning a large amount of raw data, and combined with the traditional PID control algorithm, closed-loop control of the entire drying process is achieved.

[0006] The present application provides a temperature and humidity control system for a dryer based on a neural network, the temperature and humidity control system comprising a sensor data acquisition unit, a sensor data processing unit, a heating resistor power acquisition unit, a BP neural network controller and a PID controller;

[0007] The input end of the sensor data acquisition unit is respectively connected to a drum speed sensor and a heat dissipation fan speed sensor, wherein the drum speed sensor is used to collect the speed of the dryer drum, and the heat dissipation fan speed sensor is used to collect the speed of the heat dissipation fan;

[0008] The output end of the sensor data acquisition unit is connected to the BP neural network controller through the sensor data processing unit;

[0009] The heating resistor power acquisition unit is connected to the BP neural network controller, and the heating resistor power acquisition unit is used to collect the power of the heating resistor;

[0010] The BP neural network controller is connected to the input end of the PID controller through a temperature regulating unit and a humidity regulating unit respectively. The temperature regulating unit is used to regulate the temperature of the dryer, and the humidity regulating unit is used to regulate the humidity of the dryer.

[0011] Preferably, it also includes a temperature measuring unit and a humidity measuring unit, wherein the temperature measuring unit and the humidity measuring unit are respectively connected to the output end of the PID controller, the temperature measuring unit is used to measure the real-time temperature of the dryer, and the humidity measuring unit is used to measure the real-time humidity of the dryer.

[0012] Preferably, the temperature measuring unit is also connected to a temperature regulating unit; and the humidity measuring unit is also connected to a humidity regulating unit.

[0013] Preferably, a data preprocessing module and a data feature extraction module are provided in the sensor data processing unit, the data preprocessing module is used for cleaning, correcting and filtering the collected sensor data, and the data feature extraction module is used for extracting features of the sensor data.

[0014] Preferably, a control method for a temperature and humidity control system of a dryer based on a neural network comprises the following steps:

[0015] A. The drum speed sensor and the cooling fan speed sensor respectively collect the speeds of the drum and the cooling fan, and transmit them to the BP neural network controller after being processed by the sensor data processing unit;

[0016] B. The heating resistor power acquisition unit collects the power data of the heating resistor and transmits it to the BP neural network controller;

[0017] C. The collected data is used as the input of BP neural network, the output of BP neural network is temperature and humidity data and power receipt, and multiple groups of neural network models are established;

[0018] D. Conduct deep training on multiple groups of neural network models and select the neural network model corresponding to the best performance parameters as the final model;

[0019] E. The output data is transmitted to the PID controller;

[0020] F. The PID controller controls the temperature measuring unit and the humidity measuring unit to feed back real-time temperature and humidity signals to the temperature regulating unit and the humidity regulating unit respectively;

[0021] G. The temperature adjustment unit and the humidity adjustment unit adjust the temperature and humidity of the dryer according to the feedback signal.

[0022] Preferably, the data preprocessing module processing method is as follows:

[0023] a. Clean the collected sensor data;

[0024] b. Check the cleaned data to see if there are any missing data;

[0025] c. Correct the verified data;

[0026] d. Filtering the corrected data;

[0027] e. Update the filtered data.

[0028] Preferably, the data feature extraction module extraction method is as follows:

[0029] 1) Establishing a data set, wherein the data set includes multiple sub-data sets to be feature extracted;

[0030] 2) Perform feature training on the data set to obtain a training model;

[0031] 3) extracting the first keyword and the second keyword in the data set;

[0032] 4) Circularly search each sub-data set in the data set, using the first keyword and the second keyword as initial conditions to search the sub-data set;

[0033] 5) If the first keyword or the second keyword is matched in each sub-data set, the data is extracted.

[0034] Beneficial effects:

[0035] (1) The present invention has a simple working principle and a high degree of intelligence. The BP neural network algorithm is introduced for the grain dryer, a time-varying nonlinear system with multiple inputs and outputs. The neural network model of the system is obtained by learning a large amount of original data, and combined with the traditional PID control algorithm, closed-loop control of the entire drying process is achieved.

[0036] (2) The data preprocessing module adopted in the present invention can realize data sorting, noise reduction, and data filtering, thereby improving the efficiency of subsequent data processing; the data feature extraction module adopted in the extraction method can reduce the extraction difficulty by searching the first keyword and the second keyword, improve the feature extraction accuracy, and further improve the control accuracy.

[0037] The above description is only an overview of the technical solution of the embodiment of the present application. In order to more clearly understand the technical means of the embodiment of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the embodiment of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions of the embodiments of the present application, a brief introduction will be given below to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0039] Figure 1 This is a control principle block diagram of the system of the present invention;

[0040] Figure 2 It is the structure diagram of BP neural network model;

[0041] Figure 3 The workflow of the present invention is as follows;

[0042] Explanation of the accompanying drawings: sensor data acquisition unit 1, sensor data processing unit 2, heating resistor power acquisition unit 3, BP neural network controller 4, PID controller 5, drum speed sensor 6, cooling fan speed sensor 7, temperature adjustment unit 8, humidity adjustment unit 9, temperature measurement unit 10, humidity measurement unit 11, data preprocessing module 12, data feature extraction module 13. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0044] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which this application belongs; the terms used in the specification of the application are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification, claims and drawings of this application are intended to cover non-exclusive inclusions.

[0045] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase "embodiments" in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0046] The directional words appearing in the following description are all directions shown in the drawings, and do not limit the specific structure of the present application. For example, in the description of the present application, the directions or positional relationships indicated by the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc. are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present application.

[0047] In addition, the expressions of indicated directions such as the X direction, the Y direction, and the Z direction used to illustrate the operation and construction of the components of the present embodiment are not absolute but relative, and although these indications are appropriate when the components are in the positions shown in the figures, when these positions change, these directions should be interpreted differently to correspond to the changes.

[0048] In addition, the terms "first", "second", etc. in the specification and claims of this application or the above-mentioned drawings are used to distinguish different objects rather than to describe a specific order, and may explicitly or implicitly include one or more of the features.

[0049] In the description of the present application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected" and "connected" should be understood in a broad sense. For example, the "connection" or "connection" of a mechanical structure may refer to a physical connection. For example, the physical connection may be a fixed connection, such as a fixed connection through a fixing member, such as a fixed connection through a screw, bolt or other fixing member; the physical connection may also be a detachable connection, such as a mutual snap-on or snap-fit ​​connection; the physical connection may also be an integral connection, such as a connection formed by welding, bonding or integral molding. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific circumstances.

[0050] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0051] See also Figure 1-Figure 3 , the present application discloses a temperature and humidity control system for a dryer based on a neural network, the temperature and humidity control system comprises a sensor data acquisition unit 1, a sensor data processing unit 2, a heating resistor power acquisition unit 3, a BP neural network controller 4 and a PID controller 5;

[0052] The input end of the sensor data acquisition unit 1 is respectively connected to a drum speed sensor 6 and a heat dissipation fan speed sensor 7, wherein the drum speed sensor 6 is used to collect the speed of the dryer drum, and the heat dissipation fan speed sensor 7 is used to collect the speed of the heat dissipation fan;

[0053] The output end of the sensor data acquisition unit 1 is connected to the BP neural network controller 4 through the sensor data processing unit 2;

[0054] The heating resistor power acquisition unit 3 is connected to the BP neural network controller 4, and the heating resistor power acquisition unit 3 is used to collect the power of the heating resistor;

[0055] The BP neural network controller 4 is connected to the input end of the PID controller 5 through a temperature regulating unit 8 and a humidity regulating unit 9, respectively. The temperature regulating unit 8 is used to regulate the temperature of the dryer, and the humidity regulating unit 9 is used to regulate the humidity of the dryer.

[0056] It also includes a temperature measuring unit 10 and a humidity measuring unit 11, which are respectively connected to the output end of the PID controller 5, the temperature measuring unit is used to measure the real-time temperature of the dryer, and the humidity measuring unit is used to measure the real-time humidity of the dryer; the temperature measuring unit 10 is also connected to the temperature adjustment unit 8; the humidity measuring unit 11 is also connected to the humidity adjustment unit 9.

[0057] In the present invention, a data preprocessing module 12 and a data feature extraction module 13 are provided in the sensor data processing unit 2. The data preprocessing module is used to clean, correct and filter the collected sensor data, and the data feature extraction module is used to extract features of the sensor data.

[0058] Working principle: A control method for a dryer temperature and humidity control system based on a neural network includes the following steps:

[0059] A. The drum speed sensor and the cooling fan speed sensor respectively collect the speeds of the drum and the cooling fan, and transmit them to the BP neural network controller after being processed by the sensor data processing unit;

[0060] B. The heating resistor power acquisition unit collects the power data of the heating resistor and transmits it to the BP neural network controller;

[0061] C. The collected data is used as the input of BP neural network, the output of BP neural network is temperature and humidity data and power receipt, and multiple groups of neural network models are established;

[0062] D. Conduct deep training on multiple groups of neural network models and select the neural network model corresponding to the best performance parameters as the final model;

[0063] E. The output data is transmitted to the PID controller;

[0064] F. The PID controller controls the temperature measuring unit and the humidity measuring unit to feed back real-time temperature and humidity signals to the temperature regulating unit and the humidity regulating unit respectively;

[0065] G. The temperature adjustment unit and the humidity adjustment unit adjust the temperature and humidity of the dryer according to the feedback signal.

[0066] Among them, the data preprocessing module processing method is as follows:

[0067] a. Clean the collected sensor data;

[0068] b. Check the cleaned data to see if there are any missing data;

[0069] c. Correct the verified data;

[0070] d. Filtering the corrected data;

[0071] e. Update the filtered data.

[0072] The data feature extraction module extraction method is as follows:

[0073] 1) Establishing a data set, wherein the data set includes multiple sub-data sets to be feature extracted;

[0074] 2) Perform feature training on the data set to obtain a training model;

[0075] 3) extracting the first keyword and the second keyword in the data set;

[0076] 4) Circularly search each sub-data set in the data set, using the first keyword and the second keyword as initial conditions to search the sub-data set;

[0077] 5) If the first keyword or the second keyword is matched in each sub-data set, the data is extracted.

[0078] The data preprocessing module adopted in the present invention can sort, reduce noise and filter data, thereby improving the efficiency of subsequent data processing; the data feature extraction module adopted in the extraction method can reduce the extraction difficulty, improve the feature extraction accuracy and further improve the control accuracy by searching the first keyword and the second keyword.

[0079] The present invention adopts BP neural network algorithm. On the premise of determining the main input quantity of the system and the two main output quantities of temperature and humidity, one or more hidden layers are added between the input and output. The specific number of hidden layers will be determined according to the model accuracy of the algorithm in the data training and learning process. By collecting the input and output data of multiple complete grain drying cycle ovens, this is used as a standard data sample for algorithm learning, and then a neural network system with a single hidden layer structure is preliminarily established in MATLAB. When starting to train the neural network, the weight ratio is first set according to the weight sum being 1, and the weights and hidden layers in the network are adjusted according to the error through the error back propagation path unique to the BP neural network. The activation function of the hidden layer is corrected and modified, and after repeated iterations, a BP neural network model closest to the actual one is obtained. After obtaining the model parameters, a grain dryer control system based on STM32F103C8T6 is established. The data model obtained by the BP neural network algorithm is used to calculate the standard temperature and humidity parameters at any time point in the entire drying process. This series of data is used as the set value, and the error is obtained by combining the temperature and humidity data collected by the detection system during the drying process. At this time, the traditional PID control strategy can be used to adjust some input quantities with higher weights on temperature and humidity to achieve closed-loop control of the entire drying process.

[0080] In summary, the working principle of the present invention is simple and the degree of intelligence is high. For the grain dryer, a time-varying nonlinear system with multiple inputs and outputs, a BP neural network algorithm is introduced. By learning a large amount of original data, the neural network model of the system is obtained, and combined with the traditional PID control algorithm, closed-loop control of the entire drying process is realized.

[0081] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A temperature and humidity control system for a dryer based on a neural network, characterized in that: The temperature and humidity control system comprises a sensor data acquisition unit (1), a sensor data processing unit (2), a heating resistor power acquisition unit (3), a BP neural network controller (4) and a PID controller (5); The input end of the sensor data acquisition unit (1) is respectively connected to a drum speed sensor (6) and a heat dissipation fan speed sensor (7); the drum speed sensor (6) is used to collect the speed of the dryer drum, and the heat dissipation fan speed sensor (7) is used to collect the speed of the heat dissipation fan; The output end of the sensor data acquisition unit (1) is connected to a BP neural network controller (4) via a sensor data processing unit (2); The heating resistor power acquisition unit (3) is connected to the BP neural network controller (4), and the heating resistor power acquisition unit (3) is used to acquire the power of the heating resistor; The BP neural network controller (4) is connected to the input end of the PID controller (5) via a temperature adjustment unit (8) and a humidity adjustment unit (9), respectively; the temperature adjustment unit (8) is used to adjust the temperature of the dryer, and the humidity adjustment unit (9) is used to adjust the humidity of the dryer.

2. A temperature and humidity control system for a dryer based on a neural network according to claim 1, characterized in that: It also comprises a temperature measuring unit (10) and a humidity measuring unit (11), wherein the temperature measuring unit (10) and the humidity measuring unit (11) are respectively connected to the output end of the PID controller (5), the temperature measuring unit is used to measure the real-time temperature of the dryer, and the humidity measuring unit is used to measure the real-time humidity of the dryer.

3. A temperature and humidity control system for a dryer based on a neural network according to claim 2, characterized in that: The temperature measuring unit (10) is also connected to the temperature regulating unit (8); and the humidity measuring unit (11) is also connected to the humidity regulating unit (9).

4. A temperature and humidity control system for a dryer based on a neural network according to claim 1, characterized in that: The sensor data processing unit (2) is provided with a data preprocessing module (12) and a data feature extraction module (13), wherein the data preprocessing module is used to clean, correct and filter the collected sensor data, and the data feature extraction module is used to extract features of the sensor data.

5. A control method for realizing a temperature and humidity control system of a dryer based on a neural network as claimed in claim 1, characterized in that: The control method comprises the following steps: A. The drum speed sensor and the cooling fan speed sensor respectively collect the speeds of the drum and the cooling fan, and transmit them to the BP neural network controller after being processed by the sensor data processing unit; B. The heating resistor power acquisition unit collects the power data of the heating resistor and transmits it to the BP neural network controller; C. The collected data is used as the input of BP neural network, the output of BP neural network is temperature and humidity data and power receipt, and multiple groups of neural network models are established; D. Conduct deep training on multiple groups of neural network models and select the neural network model corresponding to the best performance parameters as the final model; E. The output data is transmitted to the PID controller; F. The PID controller controls the temperature measuring unit and the humidity measuring unit to feed back real-time temperature and humidity signals to the temperature regulating unit and the humidity regulating unit respectively; G. The temperature adjustment unit and the humidity adjustment unit adjust the temperature and humidity of the dryer according to the feedback signal.

6. The control method of a temperature and humidity control system of a dryer based on a neural network according to claim 4, characterized in that: The data preprocessing module processing method is as follows: a. Clean the collected sensor data; b. Check the cleaned data to see if there are any missing data; c. Correct the verified data; d. Filtering the corrected data; e. Update the filtered data.

7. The control method of a temperature and humidity control system of a dryer based on a neural network according to claim 4, characterized in that: The data feature extraction module extraction method is as follows: 1) Establishing a data set, wherein the data set includes multiple sub-data sets to be feature extracted; 2) Perform feature training on the data set to obtain a training model; 3) extracting the first keyword and the second keyword in the data set; 4) Circularly search each sub-data set in the data set, using the first keyword and the second keyword as initial conditions to search the sub-data set; 5) If the first keyword or the second keyword is matched in each sub-data set, the data is extracted.

Images