A cardiac MRI motion artifact reduction method based on edge enhancement network.

Cardiac magnetic resonance imaging (MRI) usually requires a long acquisition time. The movement of the patients during MRI acquisition will produce image artifacts. Previous studies have shown that clear MR image texture edges are of great significance for pathological diagnosis. In this paper, a motion artifact reduction method for cardiac MRI based on edge enhancement network is proposed. Firstly, the four-plane normal vector adaptive fractional differential mask is applied to extract the edge features of blurred images. The four-plane normal vector method can reduce the noise information in the edge feature maps. The adaptive fractional order is selected according to the normal mean gradient and the local Gaussian curvature entropy of the images. Secondly, the extracted edge feature maps and blurred images are input into the de-artifact network. In this network, the edge fusion feature extraction network and the edge fusion transformer network are specially designed. The former combines the edge feature maps with the fuzzy feature maps to extract the edge feature information. The latter combines the edge attention network and the fuzzy attention network, which can focus on the blurred image edges. Finally, extensive experiments show that the proposed method can obtain higher peak signal-to-noise ratio and structural similarity index measure compared to state-of-art methods. The de-artifact images have clear texture edges.

[Research on the inner wall condition monitoring method of ring forgings based on infrared spectra].

In order to grasp the inner wall condition of ring forgings, an inner wall condition monitoring method based on infrared spectra for ring forgings is proposed in the present paper. Firstly, using infrared spectroscopy the forgings temperature measurement system was built based on the three-level FP-cavity LCTF. The two single radiation spectra from the forgings' surface were got using the three-level FP-cavity LCTF. And the temperature measuring of the surface forgings was achieved according to the infrared double-color temperature measuring principle. The measuring accuracy can be greatly improved by this temperature measurement method. Secondly, on the basis of the Laplace heat conduction differential equation the inner wall condition monitoring model was established by the method of separating variables. The inner wall condition monitoring of ring forgings was realized via combining the temperature data and the forgings own parameter information. Finally, this method is feasible according to the simulation experiment. The inner wall condition monitoring method can provide the theoretical basis for the normal operating of the ring forgings.

[Research on the temperature field detection method of hot forging based on long-wavelength infrared spectrum].

A temperature field detection method based on long-wavelength infrared spectrum for hot forging is proposed in the present paper. This method combines primary spectrum pyrometry and three-stage FP-cavity LCTF. By optimizing the solutions of three group nonlinear equations in the mathematical model of temperature detection, the errors are reduced, thus measuring results will be more objective and accurate. Then the system of three-stage FP-cavity LCTF was designed on the principle of crystal birefringence. The system realized rapid selection of any wavelength in a certain wavelength range. It makes the response of the temperature measuring system rapid and accurate. As a result, without the emissivity of hot forging, the method can acquire exact information of temperature field and effectively suppress the background light radiation around the hot forging and ambient light that impact the temperature detection accuracy. Finally, the results of MATLAB showed that the infrared spectroscopy through the three-stage FP-cavity LCTF could meet the requirements of design. And experiments verified the feasibility of temperature measuring method. Compared with traditional single-band thermal infrared imager, the accuracy of measuring result was improved.

[Research on the temperature field detection method of large cylinder forgings during heat treatment process based on infrared spectra].

In order to grasp the changes of the forging's temperature field during heat treatment, a temperature field detection method based on infrared spectra for large cylinder forgings is proposed in the present paper. On the basis of heat transfer a temperature field model of large barrel forgings was established by the method of separating variables. Using infrared spectroscopy the large forgings temperature measurement system was built based on the three-level interference filter. The temperature field detection of forging was realized in its heat treatment by combining the temperature data and the forgings temperature field detection model. Finally, this method is feasible according to the simulation experiment. The heating forging temperature detection method can provide the theoretical basis for the correct implementation of the heat treatment process.

[A method of temperature measurement for hot forging with surface oxide based on infrared spectroscopy].

High temperature large forging is covered with a thick oxide during forging. It leads to a big measurement data error. In this paper, a method of measuring temperature based on infrared spectroscopy is presented. It can effectively eliminate the influence of surface oxide on the measurement of temperature. The method can measure the surface temperature and emissivity of the oxide directly using the infrared spectrum. The infrared spectrum is radiated from surface oxide of forging. Then it can derive the real temperature of hot forging covered with the oxide using the heat exchange equation. In order to greatly restrain interference spectroscopy through included in the received infrared radiation spectrum, three interference filter system was proposed, and a group of optimal gap parameter values using spectral simulation were obtained. The precision of temperature measurement was improved. The experimental results show that the method can accurately measure the surface temperature of high temperature forging covered with oxide. It meets the requirements of measurement accuracy, and the temperature measurement method is feasible according to the experiment result.

[Research on high-precision temperature measurement system based on near infrared spectroscopy].

At present, the interference from outside radiation under the complex environment is difficult to eliminate by using the infrared thermometry method. It leads to the low measurement accuracy. In the present paper, a high-precision infrared temperature measurement system was designed. The light filter method is presented in this system. The broadband filters and three-level interference filter were combined in this method. According to the method, the near-infrared spectra sent out by high temperature object is filtered. The high temperature background light and the environment obtrusive light are filtered out. In this way, two monochromatic spectra are obtained. The radiation power ratio is received after receiving by the infrared detector. Then the temperature is obtained by calculating. In this system, the bandwidth of monochromatic spectrum permeated is only 1 nm. The inhibition of radiation from background light and ambient light except transmittance spectrum is up to 8 orders of magnitude. The measurement error caused by the ambient temperature heating of the measured object is reduced. The accuracy of the temperature measurement system is improved. Finally, the temperature measurement system is feasible according to the experiment result. The precision reached to 0.2%.