灰狼算法优化LSTM超参数-神经元个数-dropout-batch_size_lstm加优化算法

1、摘要

本文主要讲解：使用灰狼算法优化LSTM超参数-神经元个数-dropout-batch_size
主要思路：

1. 灰狼算法 Parameters ： 迭代次数、狼的寻值范围、狼的数量
2. LSTM Parameters 神经网络第一层神经元个数、神经网络第二层神经元个数、dropout比率、batch_size
3. 开始搜索：初始化所有狼的位置、迭代寻优、返回超出搜索空间边界的搜索代理、计算每个搜索代理的目标函数、更新 Alpha, Beta, and Delta
4. 训练模型，使用灰狼算法找到的最好的全局最优参数
5. plt.show()

2、数据介绍

zgpa_train.csv
DIANCHI.csv

需要数据的话去我其他文章的评论区
可接受定制

3、相关技术

灰狼优化算法(GWO),灵感来自于灰狼.GWO算法模拟了自然界灰狼的领导层级和狩猎机制.四种类型的灰狼。此外，还实现了狩猎的三个主要步骤:寻找猎物、包围猎物和攻击猎物。

PSO与GWO对比试验结果如下图：
灰狼算法

4、完整代码和步骤

此程序运行代码版本为：

tensorflow==2.5.0
numpy==1.19.5
keras==2.6.0
matplotlib==3.5.2
1
2
3
4

代码输出如下：

主运行程序入口
LSTM_GWO.py

import math
import os
import random

import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
from sklearn.metrics import mean_squared_error
from sklearn.preprocessing import MinMaxScaler
from tensorflow.python.keras.callbacks import EarlyStopping
from tensorflow.python.keras.layers import Dense, Dropout, LSTM
from tensorflow.python.keras.layers.core import Activation
from tensorflow.python.keras.models import Sequential
import numpy as numpy

os.chdir(r'D:\项目\PSO-LSTM\具体需求')
'''
灰狼算法优化LSTM
'''
plt.rcParams['font.sans-serif'] = ['SimHei']  # 用来正常显示中文标签
plt.rcParams['axes.unicode_minus'] = False  # 用来正常显示负号


def GWO(objf, lb, ub, dim, SearchAgents_no, Max_iter):
    # ===初始化 alpha, beta, and delta_pos=======
    Alpha_pos = numpy.zeros(dim)  # 位置.形成30的列表
    Alpha_score = float("inf")  # 这个是表示“正负无穷”,所有数都比 +inf 小；正无穷：float("inf"); 负无穷：float("-inf")

    Beta_pos = numpy.zeros(dim)
    Beta_score = float("inf")

    Delta_pos = numpy.zeros(dim)
    Delta_score = float("inf")  # float() 函数用于将整数和字符串转换成浮点数。

    # ====list列表类型=============
    if not isinstance(lb, list):  # 作用：来判断一个对象是否是一个已知的类型。其第一个参数（object）为对象，第二个参数（type）为类型名，若对象的类型与参数二的类型相同则返回True
        lb = [lb] * dim  # 生成[100，100，.....100]30个
    if not isinstance(ub, list):
        ub = [ub] * dim

    # ========初始化所有狼的位置===================
    Positions = numpy.zeros((SearchAgents_no, dim))
    for i in range(dim):  # 形成5*30个数[-100，100)以内
        Positions[:, i] = numpy.random.uniform(0, 1, SearchAgents_no) * (ub[i] - lb[i]) + lb[
            i]  # 形成[5个0-1的数]*100-（-100）-100
    Convergence_curve = numpy.zeros(Max_iter)

    # ========迭代寻优=====================
    for l in range(0, Max_iter):  # 迭代1000
        for i in range(0, SearchAgents_no):  # 5
            # ====返回超出搜索空间边界的搜索代理====
            for j in range(dim):  # 30
                Positions[i, j] = numpy.clip(Positions[i, j], lb[j], ub[
                    j])  # clip这个函数将将数组中的元素限制在a_min(-100), a_max(100)之间，大于a_max的就使得它等于 a_max，小于a_min,的就使得它等于a_min。

            # ===计算每个搜索代理的目标函数==========
            fitness = objf(Positions[i, :])  # 把某行数据带入函数计算
            # print("经过计算得到：",fitness)

            # ====更新 Alpha, Beta, and Delta================
            if fitness < Alpha_score:
                Alpha_score = fitness  # Update alpha
                Alpha_pos = Positions[i, :].copy()

            if (fitness > Alpha_score and fitness < Beta_score):
                Beta_score = fitness  # Update beta
                Beta_pos = Positions[i, :].copy()

            if (fitness > Alpha_score and fitness > Beta_score and fitness < Delta_score):
                Delta_score = fitness  # Update delta
                Delta_pos = Positions[i, :].copy()

        # ===========以上的循环里，Alpha、Beta、Delta===========
        a = 2 - l * ((2) / Max_iter)  # a从2线性减少到0

        for i in range(0, SearchAgents_no):
            for j in range(0, dim):
                r1 = random.random()  # r1 is a random number in [0,1]主要生成一个0-1的随机浮点数。
                r2 = random.random()  # r2 is a random number in [0,1]

                A1 = 2 * a * r1 - a  # Equation (3.3)
                C1 = 2 * r2  # Equation (3.4)
                # D_alpha表示候选狼与Alpha狼的距离
                D_alpha = abs(C1 * Alpha_pos[j] - Positions[
                    i, j])  # abs() 函数返回数字的绝对值。Alpha_pos[j]表示Alpha位置，Positions[i,j])候选灰狼所在位置
                X1 = Alpha_pos[j] - A1 * D_alpha  # X1表示根据alpha得出的下一代灰狼位置向量

                r1 = random.random()
                r2 = random.random()

                A2 = 2 * a * r1 - a  #
                C2 = 2 * r2

                D_beta = abs(C2 * Beta_pos[j] - Positions[i, j])
                X2 = Beta_pos[j] - A2 * D_beta

                r1 = random.random()
                r2 = random.random()

                A3 = 2 * a * r1 - a
                C3 = 2 * r2

                D_delta = abs(C3 * Delta_pos[j] - Positions[i, j])
                X3 = Delta_pos[j] - A3 * D_delta

                Positions[i, j] = (X1 + X2 + X3) / 3  # 候选狼的位置更新为根据Alpha、Beta、Delta得出的下一代灰狼地址。

        Convergence_curve[l] = Alpha_score

        if (l % 1 == 0):
            print(['迭代次数为' + str(l) + ' 的迭代结果' + str(Alpha_score)])  # 每一次的迭代结果
    # 绘图
    plt.plot(Convergence_curve)
    plt.title('Convergence_curve')
    plt.show()

    print("The best solution obtained by GWO is : " + str(Alpha_pos))
    print("The best optimal value of the objective funciton found by GWO is : " + str(Alpha_score))
    return Alpha_pos,Alpha_score


def creat_dataset(dataset, look_back):
    dataX, dataY = [], []
    for i in range(len(dataset) - look_back - 1):
        a = dataset[i: (i + look_back)]
        dataX.append(a)
        dataY.append(dataset[i + look_back])
    return np.array(dataX), np.array(dataY)


dataframe = pd.read_csv('zgpa_train.csv', header=0, parse_dates=[0], index_col=0, usecols=[0, 5], squeeze=True)
dataset = dataframe.values
data = pd.read_csv('DIANCHI.csv', header=0)
z = data['fazhi']

scaler = MinMaxScaler(feature_range=(0, 1))
dataset = scaler.fit_transform(dataset.reshape(-1, 1))

train_size = int(len(dataset) * 0.8)
test_size = len(dataset) - train_size
train, test = dataset[0: train_size], dataset[train_size: len(dataset)]
look_back = 10
trainX, trainY = creat_dataset(train, look_back)
testX, testY = creat_dataset(test, look_back)


def build_model(neurons1, neurons2, dropout):
    X_train, y_train = trainX, trainY
    X_test, y_test = testX, testY
    model = Sequential()

    # model.add(LSTM(input_dim=1, units=50, return_sequences=True))
    model.add(LSTM(input_dim=neurons1, units=50, return_sequences=True, input_shape=(10, 1)))

    # model.add(LSTM(input_dim=50, units=100, return_sequences=True))
    model.add(LSTM(input_dim=neurons2, units=100, return_sequences=True))

    model.add(LSTM(input_dim=100, units=200, return_sequences=True))
    model.add(LSTM(300, return_sequences=False))

    # model.add(Dropout(0.2))
    model.add(Dropout(dropout))

    model.add(Dense(100))
    model.add(Dense(units=1))
    model.add(Activation('relu'))
    model.compile(loss='mean_squared_error', optimizer='Adam')
    return model, X_train, y_train, X_test, y_test


def training(X):
    neurons1 = int(X[0])
    neurons2 = int(X[1])
    dropout = round(X[2], 6)
    batch_size = int(X[3])
    print(X)
    model, X_train, y_train, X_test, y_test = build_model(neurons1, neurons2, dropout)
    model.fit(
        X_train,
        y_train,
        batch_size=batch_size,
        epochs=1,
        validation_split=0.1,
        verbose=0,
        callbacks=[EarlyStopping(monitor='val_loss', patience=22, restore_best_weights=True)])

    pred = model.predict(X_test)
    temp_mse = mean_squared_error(y_test, pred)
    print(temp_mse)
    return temp_mse


if __name__ == '__main__':
    '''
    神经网络第一层神经元个数
    神经网络第二层神经元个数
    dropout比率
    batch_size
    '''
    ub = [10, 26, 0.25, 8]
    lb = [6, 22, 0.2, 2]

    # ===========主程序================
    Max_iter = 3  # 迭代次数
    dim = 4  # 狼的寻值范围
    SearchAgents_no = 5  # 寻值的狼的数量
    Alpha_pos,Alpha_score = GWO(training, lb, ub, dim, SearchAgents_no, Max_iter)

    print('best_params is ', Alpha_pos)
    print('best_precision is', Alpha_score)

    # 训练模型  使用PSO找到的最好的神经元个数
    neurons1 = int(Alpha_pos[0])
    neurons2 = int(Alpha_pos[1])
    dropout = Alpha_pos[2]
    batch_size = int(Alpha_pos[3])
    model, X_train, y_train, X_test, y_test = build_model(neurons1, neurons2, dropout)
    history = model.fit(X_train, y_train, epochs=333, batch_size=batch_size, validation_split=0.2, verbose=1,
                        callbacks=[EarlyStopping(monitor='val_loss', patience=29, restore_best_weights=True)])
    trainPredict = model.predict(trainX)
    testPredict = model.predict(testX)
    trainPredict = scaler.inverse_transform(trainPredict)
    trainY = scaler.inverse_transform(trainY)
    testPredict = scaler.inverse_transform(testPredict)
    testY = scaler.inverse_transform(testY)

    trainScore = math.sqrt(mean_squared_error(trainY, trainPredict[:, 0]))
    # print('Train Score %.2f RMSE' %(trainScore))
    testScore = math.sqrt(mean_squared_error(testY, testPredict[:, 0]))
    # print('Test Score %.2f RMSE' %(trainScore))

    trainPredictPlot = np.empty_like(dataset)
    trainPredictPlot[:] = np.nan
    trainPredictPlot = np.reshape(trainPredictPlot, (dataset.shape[0], 1))
    trainPredictPlot[look_back: len(trainPredict) + look_back, :] = trainPredict

    testPredictPlot = np.empty_like(dataset)
    testPredictPlot[:] = np.nan
    testPredictPlot = np.reshape(testPredictPlot, (dataset.shape[0], 1))
    testPredictPlot[len(trainPredict) + (look_back * 2) + 1: len(dataset) - 1, :] = testPredict

    plt.plot(history.history['loss'])
    plt.title('model loss')
    plt.ylabel('loss')
    plt.xlabel('epoch')
    plt.show()

    fig2 = plt.figure(figsize=(20, 15))
    plt.rcParams['font.family'] = ['STFangsong']
    ax = plt.subplot(222)
    plt.plot(scaler.inverse_transform(dataset), 'b-', label='实验数据')
    plt.plot(trainPredictPlot, 'r', label='训练数据')
    plt.plot(testPredictPlot, 'g', label='预测数据')
    plt.plot(z, 'k-', label='寿命阀值RUL')
    plt.ylabel('capacity', fontsize=20)
    plt.xlabel('cycle', fontsize=20)
    plt.legend()
    name = 'neurons1_' + str(neurons1) + 'neurons2_' + str(neurons2) + '_dropout' + str(
        dropout) + '_batch_size' + str(batch_size)
    plt.savefig('D:\项目\PSO-LSTM\具体需求\photo\\' + name + '.png')
    plt.show()

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262