阅读说明：本技术 一种等离子灰渣熔融炉的控制方法 (Control method of plasma ash melting furnace ) 是由 胡明 张亮 宫臣 李小明 赵彬 肖诚斌 于 2021-07-29 设计创作，主要内容包括：本发明提供一种等离子灰渣熔融炉的控制方法,步骤包括：S1.构建BP神经网络模型,包括输入层、隐含层和输出层；S2.实时测量熔融炉的入料量、入料的溶解热、熔池深度、炉膛压力和炉膛温度作为BP神经网络的输入层,得到作为输出层的偏差率EC,并将熔融炉功率控制器的输出功率对应的温度与目标设置温度的差值记为偏差量E；S3.根据偏差率EC和偏差量E得到PID控制器的输入值Kp、Ki和Kd；S4.PID控制器同时根据Kp、Ki、Kd和偏差量E输出控制量至熔融炉的功率控制器,熔融炉功率控制器根据所述控制量调整输出功率进而调整炉膛温度；S5.重复步骤S2、S3和S4直至熔融炉炉膛温度达到预设温度。(The invention provides a control method of a plasma ash melting furnace, which comprises the following steps: s1, constructing a BP neural network model, which comprises an input layer, a hidden layer and an output layer; s2, measuring the feeding quantity of the melting furnace, the dissolution heat of the feeding material, the depth of a molten pool, the pressure of a hearth and the temperature of the hearth in real time to be used as an input layer of a BP (back propagation) neural network, obtaining a deviation rate EC used as an output layer, and recording the difference value between the temperature corresponding to the output power of a power controller of the melting furnace and a target set temperature as a deviation amount E; s3, obtaining input values Kp, Ki and Kd of the PID controller according to the deviation rate EC and the deviation quantity E; s4, the PID controller simultaneously outputs control quantity to a power controller of the melting furnace according to Kp, Ki, Kd and the deviation quantity E, and the power controller of the melting furnace adjusts output power according to the control quantity so as to adjust the temperature of the hearth; s5, repeating the steps S2, S3 and S4 until the hearth temperature of the melting furnace reaches the preset temperature.)

1. A control method of a plasma ash melting furnace is characterized in that: the method comprises the following steps:

s1, constructing a BP neural network model, which comprises an input layer, a hidden layer and an output layer, repeatedly collecting the feeding quantity of a melting furnace, the dissolution heat of the feeding, the depth of a molten pool, the pressure of a hearth and the temperature of the hearth as the input layer, taking the deviation ratio EC as the output layer, continuously learning and adjusting the weight of an input parameter according to the output temperature mapping relation of a melting furnace power controller corresponding to the deviation ratio EC, and obtaining a learned BP neural network;

s2, measuring the feeding quantity of the melting furnace, the dissolution heat of the feeding material, the depth of a molten pool, the pressure of a hearth and the temperature of the hearth in real time to be used as an input layer of a BP (back propagation) neural network, obtaining a deviation rate EC used as an output layer, and recording the difference value between the temperature corresponding to the output power of a power controller of the melting furnace and a target set temperature as a deviation amount E;

s3, obtaining input values Kp, Ki and Kd of the PID controller according to the deviation rate EC and the deviation quantity E;

s4, the PID controller simultaneously outputs control quantity to a power controller of the melting furnace according to Kp, Ki, Kd and the deviation quantity E, and the power controller of the melting furnace adjusts output power according to the control quantity so as to adjust the temperature of the hearth;

s5, repeating the steps S2, S3 and S4 until the hearth temperature of the melting furnace reaches the preset temperature.

2. The method of controlling a plasma ash melting furnace according to claim 1, characterized in that: in step S1, the number of neurons in the hidden layer of the BP neural network model is seven, and the number of neurons corresponds to the input 7 fuzzy subsets NB, NM, NS, ZO, PS, PM, and PB, respectively.

3. The control method of a plasma ash melting furnace according to claim 2, characterized in that: step S3 first deblurs EC and E to obtain equal distributions of-5, -4, -3, -2, -1, 0, 1, 2, 3, 4, and 5, respectively, by:

wherein M is E or EC, PV is the temperature value of the hearth, SP is the target set temperature value, and RH is the upper limit of the measuring range of the instrument;

kp, Ki and Kd were then obtained by EC and E as shown in the following table:

kp membership degree change table:

ki membership degree change table:

kd membership change table:

4. the method of controlling a plasma ash melting furnace according to claim 1, characterized in that: step S4 the melting furnace power controller calculates the output power P according to the control quantity outputted by the PID controller_dAnd regulating the furnace temperature by adjusting the output voltage and the output current, the output voltage being based onIs obtained, wherein the arc is ignitedPress U_aRectified output voltage U_dH is system reactance, R is system resistance, K₃Is a constant regulation factor, the output current I_dAccording toThus obtaining the product.

Technical Field

The invention belongs to the technical field of plasma ash melting furnaces, and particularly relates to a control method of a plasma ash melting furnace.

Background

The control of the plasma ash melting furnace is a typical complex process with large inertia, large hysteresis, nonlinearity and time-varying property, and an accurate mathematical model is difficult to establish by a mathematical method. At present, the main control method only performs univariate control on the temperature, such as univariate PID control, univariate fuzzy control and the like. In the actual operation control process, a plurality of factors influencing the temperature of the furnace condition are found, and besides the temperature, other parameters such as the feeding amount, the dissolution heat of the feeding material, the depth of a molten pool and the pressure of a furnace chamber can cause the fluctuation of the temperature of the furnace chamber. A good control effect cannot be obtained in actual operation using only the univariate control.

Disclosure of Invention

In order to solve the technical problems, the invention provides the following technical scheme:

a control method of a plasma ash melting furnace comprises the following steps:

s1, constructing a BP neural network model, which comprises an input layer, a hidden layer and an output layer, repeatedly collecting the feeding quantity of a melting furnace, the dissolution heat of the feeding, the depth of a molten pool, the pressure of a hearth and the temperature of the hearth as the input layer, taking the deviation ratio EC as the output layer, continuously learning and adjusting the weight of an input parameter according to the output temperature mapping relation of a melting furnace power controller corresponding to the deviation ratio EC, and obtaining a learned BP neural network;

s2, measuring the feeding quantity of the melting furnace, the dissolution heat of the feeding material, the depth of a molten pool, the pressure of a hearth and the temperature of the hearth in real time to be used as an input layer of a BP (back propagation) neural network, obtaining a deviation rate EC used as an output layer, and recording the difference value between the temperature corresponding to the output power of a power controller of the melting furnace and a target set temperature as a deviation amount E;

s3, obtaining input values Kp, Ki and Kd of the PID controller according to the deviation rate EC and the deviation quantity E;

s4, the PID controller simultaneously outputs control quantity to a power controller of the melting furnace according to Kp, Ki, Kd and the deviation quantity E, and the power controller of the melting furnace adjusts output power according to the control quantity so as to adjust the temperature of the hearth;

s5, repeating the steps S2, S3 and S4 until the hearth temperature of the melting furnace reaches the preset temperature.

Further, in step S1, the number of neurons in the hidden layer of the BP neural network model is seven, and the number of neurons corresponds to the input 7 fuzzy subsets NB, NM, NS, ZO, PS, PM, PB, respectively.

Further, step S3 first deblurrs EC and E by the following equations to obtain the equal distribution of-5, -4, -3, -2, -1, 0, 1, 2, 3, 4, and 5, respectively:

wherein M is C or EC, PV is the temperature value of the hearth, SP is the target set temperature value, and RH is the upper limit of the measuring range of the instrument;

kp, Ki and Kd were then obtained by EC and E as shown in the following table:

kp membership degree change table:

ki membership degree change table:

kd membership change table:

further, the melting furnace power controller calculates the output power P according to the control amount outputted from the PID controller at step S4_dAnd regulating the furnace temperature by adjusting the output voltage and the output current, the output voltage being based onTo obtain an arc point voltage U_aRectified output voltage U_dH is system reactance, R is system resistance, K₃Is a constant regulation factor, the output current I_dAccording toThus obtaining the product.

The invention has the beneficial effects that: the actual control effect of the plasma ash melting furnace through the traditional single-loop PID control and the control model and algorithm provided by the patent is compared as follows:

(1) the performance indexes of the traditional single-loop PID control are as follows: the stable time Ts is 160 seconds, the overshoot delta% is 50%, the steady state error is 5%, and the anti-interference performance is poor.

(2) Performance indexes after learning are performed through 2000 groups of samples by using the patent control and algorithm: the stable time Ts is 20 seconds, the overshoot delta% is 0%, the steady state error is 1%, and the anti-interference performance is strong.

(3) From the comparison, the stability time of the system using the algorithm is reduced from 160 seconds to 20 seconds, the overshoot and the steady-state error are almost zero, and the anti-interference performance is strong. Therefore, the control and algorithm provided by the patent are obviously superior to the traditional PID control through the verification of a debugging result.

Drawings

FIG. 1 is a schematic diagram of the control scheme of an embodiment of the present invention;

FIG. 2 is a block diagram of a BP neural network according to an embodiment of the present invention;

FIG. 3 is a flowchart of a BP neural network-fuzzy PID algorithm program according to an embodiment of the present invention.

Detailed Description

The present invention is further described with reference to the following examples, which are provided for illustration only and are not to be construed as limiting the scope of the claims, and other alternatives which may occur to those skilled in the art are also within the scope of the claims.

Example 1

A control method of a plasma ash melting furnace, as shown in fig. 1, comprising the steps of:

s1, constructing a BP neural network model, which comprises an input layer, a hidden layer and an output layer, repeatedly collecting the feeding quantity of a melting furnace, the dissolution heat of the feeding, the depth of a molten pool, the pressure of a hearth and the temperature of the hearth as the input layer, taking the deviation ratio EC as the output layer, continuously learning and adjusting the weight of an input parameter according to the output temperature mapping relation of the deviation ratio EC corresponding to a power controller of the melting furnace, and obtaining the learned BP neural network, wherein the BP neural network continuously adjusts the weight and the threshold of the input parameter by learning and inputting each parameter and the output mapping relation through a gradient descent method to enable a control point to approach a set point, the operation mode of a BP neural network program is a cycle operation, the maximum learning times are set, and whether an error meets the requirement or not is judged through an error function. When the preset precision is reached or the learning times are more than the set maximum times, ending the algorithm;

s2, measuring the feeding quantity of the melting furnace, the dissolution heat of the feeding material, the depth of a molten pool, the pressure of a hearth and the temperature of the hearth in real time to be used as an input layer of a BP (back propagation) neural network, obtaining a deviation rate EC used as an output layer, and recording the difference value between the temperature corresponding to the output power of a power controller of the melting furnace and a target set temperature as a deviation amount E;

s3, obtaining input values Kp, Ki and Kd of the PID controller according to the deviation rate EC and the deviation quantity E;

s4, the PID controller simultaneously outputs control quantity to a power controller of the melting furnace according to Kp, Ki, Kd and the deviation quantity E, and the power controller of the melting furnace adjusts output power according to the control quantity so as to adjust the temperature of the hearth;

s5, repeating the steps S2, S3 and S4 until the hearth temperature of the melting furnace reaches the preset temperature.

In step S1, the number of neurons in the hidden layer of the BP neural network model is seven, and as shown in fig. 2, the number of neurons corresponds to the input 7 fuzzy subsets NB, NM, NS, ZO, PS, PM, PB, respectively.

Step S3 first deblurs EC and E to obtain equal distributions of-5, -4, -3, -2, -1, 0, 1, 2, 3, 4, and 5, respectively, by:

: the method comprises the steps of rounding upwards, wherein M is C or EC, PV is a furnace temperature value, SP is a target set temperature value, and RH is an upper limit of the meter measuring range;

kp, Ki and Kd were then obtained by EC and E as shown in the following table:

kp membership degree change table:

ki membership degree change table:

kd membership change table:

step S4 the melting furnace power controller calculates the output power P according to the control quantity outputted by the PID controller_dAnd regulating the furnace temperature by adjusting the output voltage and the output current, the output voltage being based onTo obtain an arc point voltage U_aRectified output voltage U_dH is system reactance, R is system resistance, K₃Is a constant regulation factor, the output current I_dAccording toThus obtaining the product.

The actual control effect of the plasma ash melting furnace through the traditional single-loop PID control and the control model and algorithm provided by the patent is compared as follows:

1. the performance indexes of the traditional single-loop PID control are as follows: the stable time Ts is 160 seconds, the overshoot delta% is 50%, the steady state error is 5%, and the anti-interference performance is poor.

2. Performance indexes after learning are performed through 2000 groups of samples by using the patent control and algorithm: the stable time Ts is 20 seconds, the overshoot delta% is 0%, the steady state error is 1%, and the anti-interference performance is strong.

3. From the comparison, the stability time of the system using the algorithm is reduced from 160 seconds to 20 seconds, the overshoot and the steady-state error are almost zero, and the anti-interference wall is realized. Therefore, the control and algorithm provided by the patent are obviously superior to the traditional PID control through the verification of a debugging result. It should be noted that the above-mentioned embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, which should be covered by the claims of the present invention.