English for Science and Technology (EST), as a special language style, is widely used in the field of Science and Technology. For this kind of articles, the requirements of translation quality are relatively high. Therefore, this paper studies a quality evaluation method of Sci-Tech English translation for cross-cultural communication. As statistical machine translation has almost reached the limits of its capacity, neural machine translation is becoming the technology of the future. This paper also describes the evaluation of machine translation quality with and automatic evaluation process with machine learning technology. The evaluation index of EST translation quality is selected according to the selection principle and expert consultation method. Then, the weight of the index is calculated by using the analytic hierarchy process. Finally, the translation quality evaluation is given by using the fuzzy comprehensive evaluation, glass-box and black-box evaluation with machine learning method. The results show that under the application of the research method, the evaluation results are completely corresponding to the actual competition results of four competitors, which proves the effectiveness of the research method.