BackgroundMalignant melanoma of oral cavity is a rare condition, accounting for 0.5 % of all oral malignancies and about 1–2 % of all melanomas. Oral melanomas have extremely poor prognosis with 5 years survival rate of 12.3 %. The poor prognosis compared to cutaneous melanoma may be attributed to delay in reporting by patient and diagnosis, and apt to become ulcerated due to repeated trauma. The ‘chameleonic’ presentation of a mainly asymptomatic condition, the rarity of these lesions, the poor prognosis and the necessity of a highly specialized treatment are factors that should be seriously considered by the involved health provider.Case presentationWe present a case of 32 years old male of Han ethnicity with mucosal melanoma of upper lip, comparing his clinical presentation and histological findings at his first visit and following the recurrence. The patient complained of black discoloration on the left side of upper lip since 4 years which gradually increased in size and later involved the skin of the lip. Excision with 5 mm safety margin was performed but the patient presented with the similar lesion after three and half years of the treatment. So, again wide excision with 2 cm safety margin was performed followed by reconstruction of the lip.ConclusionThis case provides an example of aggressive behavior of mucosal melanoma and emphasizes on the fact that any pigmented lesion detected in the oral cavity may exhibit potential growth and should be submitted to biopsy to exclude malignancy. It also exemplifies of how the time of diagnosis and the evolution of a disease could be seriously influenced by patient’s behavior.

No abstract

Satellite mission planning is the basis and top-level work of space missions and the beginning of each space mission. Therefore, the scientific research of satellite mission planning is very important. By analyzing the existing research results, we can know that the research on task planning mainly focuses on three aspects: research objects, established model, and solution algorithm. Starting from these three aspects vertically and then horizontally, this paper comprehensively discusses the theoretical basis, application, and advantages and disadvantages of related technologies in the research literature in recent years. Finally, based on the research on satellite mission planning, this paper puts forward its own views on the future development direction and research focus.

This paper investigates the application of particle swarm optimization (PSO) algorithm to plan joint trajectories of the space modular reconfigurable satellite (SMRS). SMRS changes its configuration by joint motions to complete various space missions; its movement stability is affected by joints motions because of the dynamic coupling effect in space. To improve the movement stability in reconfiguration progress, this paper establishes the optimization object equation to characterize the movement stability of SMRS in its reconfiguration process. The velocity-level and position-level kinematic models based on the proposed virtual joint coordinate system of SMRS are derived. The virtual joint coordinate system solves the problem of asymmetric joint coordinate system resulted by the asymmetric joint arrangement of SMRS. The six-order and seven-order polynomial curves are chosen to parameterize the joint trajectories and ensure the continuous position, velocity, and acceleration of joint motions. Finally, PSO algorithm is used to optimize the trajectory parameters in two cases. Consistent optimization results in terms of the six-order and seven-order polynomial in both cases prove the PSO algorithm can be effectively used for joint trajectory planning of SMRS.

This paper is devoted to model-free attitude control of rigid spacecraft in the presence of control torque saturation and external disturbances. Specifically, a model-free deep reinforcement learning (DRL) controller is proposed, which can learn continuously according to the feedback of the environment and realize the high-precision attitude control of spacecraft without repeatedly adjusting the controller parameters. Considering the continuity of state space and action space, the Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm based on actor-critic architecture is adopted. Compared with the Deep Deterministic Policy Gradient (DDPG) algorithm, TD3 has better performance. TD3 obtains the optimal policy by interacting with the environment without using any prior knowledge, so the learning process is time-consuming. Aiming at this problem, the PID-Guide TD3 algorithm is proposed, which can speed up the training speed and improve the convergence precision of the TD3 algorithm. Aiming at the problem that reinforcement learning (RL) is difficult to deploy in the actual environment, the pretraining/fine-tuning method is proposed for deployment, which can not only save training time and computing resources but also achieve good results quickly. The experimental results show that DRL controller can realize high-precision attitude stabilization and attitude tracking control, with fast response speed and small overshoot. The proposed PID-Guide TD3 algorithm has faster training speed and higher stability than the TD3 algorithm.