""" X光数据处理模块 包含自动选择圆弧区间、拟合和数据校正等功能 """ import numpy as np import pandas as pd from scipy.optimize import curve_fit from scipy.ndimage import gaussian_filter1d import os.path import struct from scipy.signal import argrelextrema, savgol_filter class XRayDataProcessor: def __init__(self): """初始化X光数据处理器""" # 初始化数据存储 self.data = None self.index_data = None self.channel_data = None self.smoothed_data = None self.derivative_data = None self.results = None self.selected_spans = {'CH1': [], 'CH2': []} self.pipe_diameter = 130 def set_pipe_diameter(self, diameter): """设置管道直径""" self.pipe_diameter = diameter def load_data(self, filepath): """加载CSV数据文件""" try: self.data = pd.read_csv(filepath) self.channel_data = { 'CH1': self.data['CH1'].values.astype(float), 'CH2': self.data['CH2'].values.astype(float) } try: self.index_data = self.data['INDEX'].values.astype(int) except: self.index_data = np.arange(len(self.channel_data['CH1'])) # 计算平滑数据和导数 self.calculate_smoothed_and_derivative() return True except Exception as e: print(f"加载数据出错: {str(e)}") return False def calculate_smoothed_and_derivative(self, sigma=2.0): """计算高斯滤波平滑数据和一阶导数""" try: if self.channel_data is None: return False # 为每个通道计算平滑数据和导数 self.smoothed_data = {} self.derivative_data = {} for ch in self.channel_data.keys(): # 使用高斯滤波平滑数据 smoothed = gaussian_filter1d(self.channel_data[ch], sigma) self.smoothed_data[ch] = smoothed # 计算平滑数据的一阶导数 derivative = np.gradient(smoothed, self.index_data) self.derivative_data[ch] = derivative return True except Exception as e: print(f"计算平滑数据和导数出错: {str(e)}") return False def find_outer_peak(self, data, sigma=2.0, peak_threshold=0.15): """ 找到一阶导数绝对值的主要极值点,作为圆弧的外侧 """ # 1. 平滑数据,消除噪声 smoothed = gaussian_filter1d(data, sigma=sigma) # 2. 从头开始,若第data[k] - data[k + 50] > data[k] * 0.2,说明k是外侧极值点 if len(data) < 1000: return [0, 0] outer_peaks = [0, 0] for k in range(len(data) - 50): if smoothed[k] - smoothed[k + 50] > smoothed[k] * peak_threshold: outer_peaks[0] = k break # 3. 从尾开始,若第data[k] - data[k - 50] > data[k] * 0.2,说明k是外侧极值点 for k in range(len(data) - 50, 0, -1): if smoothed[k] - smoothed[k - 50] > smoothed[k] * peak_threshold: outer_peaks[1] = k break return outer_peaks def find_derivative_peaks(self, deriv_data, sigma=5, peak_threshold=0.3): """ 精准找出一阶导数绝对值的主要极值点 :param deriv_data: 一阶导数数组(CH1或CH2的一阶导数) :param sigma: 平滑窗口大小,建议5-11,越大去噪越强 :param peak_threshold: 峰值过滤比例(0-1),越大越严格 :return: 峰值索引列表,按强度从高到低排序 """ # 1. 平滑一阶导数,消除噪声 deriv_smooth = savgol_filter(deriv_data, window_length=sigma, polyorder=2) # 2. 取绝对值,让正负跳变都变成正向峰值 deriv_abs = np.abs(deriv_smooth) # 3. 找所有局部极大值点 all_peaks_idx = argrelextrema(deriv_abs, np.greater)[0] if len(all_peaks_idx) == 0: return [] # 4. 按峰值强度排序,过滤掉小噪声峰 peak_values = deriv_abs[all_peaks_idx] sorted_idx = all_peaks_idx[np.argsort(peak_values)[::-1]] # 从大到小排序 # 只保留强度超过「最大峰值×阈值」的主峰值 max_peak = deriv_abs.max() valid_peaks = [idx for idx in sorted_idx if deriv_abs[idx] >= max_peak * peak_threshold] max4 = sorted([int(x) for x in valid_peaks[:4]]) print(max4) return max4 # 最多返回前4个最强峰 def auto_select_arcs(self): """自动选择两侧的圆弧部分,对CH1和CH2通道分别处理""" if self.index_data is None or len(self.index_data) < 10: print("无可用数据") return False try: # 清除之前的选择 self.selected_spans = {'CH1': [], 'CH2': []} # 确保已计算平滑数据和导数 if self.derivative_data is None: self.calculate_smoothed_and_derivative() if self.derivative_data is None: print("无法计算导数数据") return False # 为两个通道分别寻找区间 ch1_spans = self._find_spans_for_channel('CH1') ch2_spans = self._find_spans_for_channel('CH2') if ch1_spans == [] or ch2_spans == []: return False # 为每个通道存储各自的区间 success_count = 0 if ch1_spans: self.selected_spans['CH1'] = ch1_spans print(f"已为CH1通道选择{len(ch1_spans)}个区间") success_count += 1 if ch2_spans: self.selected_spans['CH2'] = ch2_spans print(f"已为CH2通道选择{len(ch2_spans)}个区间") success_count += 1 if success_count == 0: # 两个通道都失败 print("两个通道均未能找到合适的区间,请尝试手动选择") return False return True except Exception as e: print(f"自动选择过程中出错: {str(e)}") return False def _find_spans_for_channel(self, channel): """为指定通道寻找合适的区间""" data = self.channel_data[channel] n = len(self.index_data) potential_extremes = self.find_outer_peak(data) # 至少有两个极值点,选择第一个和最后一个 p1 = potential_extremes[0] p2 = potential_extremes[-1] if p1 == 0 and p2 == 0: return [] # 计算区间边界: [p1*0.2, p1*0.9], [(n-p2)*0.1+p2, (n-p2)*0.7+p2] left_start_idx = max(0, int(p1 * 0.01)) left_end_idx = min(n-1, int(p1)) right_start_idx = min(n-1, p2) right_end_idx = min(n-1, int(n - (n - p2) * 0.01)) # 转换为INDEX值 left_span = (self.index_data[left_start_idx], self.index_data[left_end_idx]) right_span = (self.index_data[right_start_idx], self.index_data[right_end_idx]) # 记录找到的极值点信息 print(f"{channel} 通道找到极值点: p1={p1}, p2={p2},区间: 左=({left_start_idx},{left_end_idx}), 右=({right_start_idx},{right_end_idx})") spans = [left_span, right_span] return spans def set_manual_spans(self, spans, channel=None): """手动设置区间列表 参数: spans: 区间列表或字典 channel: 指定通道,None表示设置所有通道 """ if channel is not None and channel in ['CH1', 'CH2']: self.selected_spans[channel] = spans else: # 如果是字典格式,分别设置每个通道 if isinstance(spans, dict): for ch in ['CH1', 'CH2']: if ch in spans: self.selected_spans[ch] = spans[ch] else: # 否则设置所有通道为相同的区间 self.selected_spans = {'CH1': spans, 'CH2': spans} return True def fit_data(self): """根据选择的区间拟合数据""" # 检查是否有任何通道选择了区间 if not any(self.selected_spans.values()): print("请先选择至少一个数据区间") return False try: self.results = {} # 为每个通道分别进行拟合 for ch in ['CH1', 'CH2']: if not self.selected_spans[ch]: print(f"{ch}通道未选择区间,跳过拟合") continue print(f"{ch}通道选择的区间: {self.selected_spans[ch]}") # 合并当前通道所有选中的数据点 selected_indices = [] for span in self.selected_spans[ch]: indices_in_span = np.where((self.index_data >= span[0]) & (self.index_data <= span[1]))[0] selected_indices.extend(indices_in_span) # 确保索引是唯一的并且排序 selected_indices = sorted(list(set(selected_indices))) if len(selected_indices) < 10: print(f"{ch}通道选择的数据点太少({len(selected_indices)}个),无法进行可靠拟合") continue # 提取选中区间的数据 selected_index_data = self.index_data[selected_indices] selected_channel_data = self.channel_data[ch][selected_indices] # 分析数据 self.results[ch] = self._analyze_channel(ch, selected_channel_data, selected_index_data) # 计算拟合曲线(对全部数据范围) full_indices = self.index_data params = self.results[ch]['params_opt'] self.results[ch]['Q_fit_full'] = self._model(full_indices, *params) self.results[ch]['index_full'] = full_indices # 检查是否有成功拟合的通道 if not self.results: print("没有通道成功进行拟合") return False self._print_fit_results() return True except Exception as e: print(f"拟合过程中出错: {str(e)}") return False def _model(self, index, Q0, mu, offset): """X光束衰减模型""" R = self.pipe_diameter / 2 t = 0.8 factor = 0.04 X = factor * (index - offset) X_clip = np.clip(X, -(R-1), R-1) term1 = np.sqrt((R + t)**2 - X_clip**2) term2 = np.sqrt(R**2 - X_clip**2) L = 2 * (term1 - term2) return Q0 * np.exp(-mu * L) def _analyze_channel(self, channel_name, Q_data, index_data): """分析单个通道的数据""" # 参数设置 initial_guess = [np.max(Q_data)*2, 0.4, np.max(index_data) * 0.5] bounds = ( [np.max(Q_data), 0.3, np.max(index_data) * 0.2], [3*np.max(Q_data), 0.5, np.max(index_data) * 0.8] ) # 执行拟合 params_opt, params_cov = curve_fit( self._model, index_data, Q_data, p0=initial_guess, bounds=bounds, maxfev=10000 ) # 结果存储 return { 'params_opt': params_opt, 'params_cov': params_cov } def _print_fit_results(self): """打印拟合结果参数""" print("双通道拟合参数对比:") for ch in ['CH1', 'CH2']: p = self.results[ch]['params_opt'] e = np.sqrt(np.diag(self.results[ch]['params_cov'])) print(f"\n{ch}通道 {self.pipe_diameter}:") print(f"Q0 = {p[0]:.1f} ± {e[0]:.1f}") print(f"μ = {p[1]:.6f} ± {e[1]:.6f} mm⁻¹") print(f"offset = {p[2]:.1f} ± {e[2]:.1f}") def correct_data(self): """根据拟合曲线校正数据""" if self.results is None: print("请先进行数据拟合") return None try: # 根据最大拟合值计算校正系数 correction_factors = {} corrected_data = {} for ch in ['CH1', 'CH2']: # 获取当前通道的拟合结果 res = self.results[ch] # 计算全部数据范围的拟合值 full_fit_values = res['Q_fit_full'] # 已经是全部数据范围的拟合值 # 计算拟合曲线的最大值Q1 Q1 = np.max(full_fit_values) # 为每个点计算校正系数,避免除以0 safe_fit_values = np.maximum(full_fit_values, 0.1) # 避免除以0 # 计算校正系数:拟合值/最大拟合值 factors = safe_fit_values / Q1 # 存储校正系数和校正后的数据 correction_factors[ch] = factors corrected_data[ch] = self.channel_data[ch] / factors return { 'index_data': self.index_data, 'original_data': self.channel_data, 'corrected_data': corrected_data } except Exception as e: print(f"数据校正过程中出错: {str(e)}") return None def save_corrected_data(self, corrected_result, output_path, trim_edges=True, trim_amount=200): """保存校正后的数据 参数: corrected_result: correct_data()方法的返回结果 output_path: 输出文件路径 trim_edges: 是否裁剪边缘数据 trim_amount: 裁剪数量,头尾各裁剪的点数 """ try: if corrected_result is None: print("没有校正数据可保存") return None,None,None index_data = corrected_result['index_data'] original_data = corrected_result['original_data'] corrected_data = corrected_result['corrected_data'] # 检查数据长度 data_length = len(index_data) # 如果需要裁剪但数据不足 if trim_edges and data_length <= 2 * trim_amount: print(f"数据总长度为{data_length}点,不足以去掉头尾各{trim_amount}点。") print("将保存全部数据。") trim_edges = False # 确定数据范围 if trim_edges: start_idx = trim_amount end_idx = data_length - trim_amount else: start_idx = 0 end_idx = data_length # 创建要保存的数据 save_data = { 'INDEX': index_data[start_idx:end_idx] } # 添加原始数据和校正后的数据 for ch in corrected_data.keys(): save_data[f'{ch}_原始'] = original_data[ch][start_idx:end_idx] save_data[f'{ch}'] = corrected_data[ch][start_idx:end_idx] channel_A = [] channel_B = [] for value in save_data['CH1']: channel_A.append(int(value)) for value in save_data['CH2']: channel_B.append(int(value)) # print("channel_A",channel_A) file_content = bytearray() for i in range (len(channel_A)): file_content.extend(struct.pack('