Research progress on key technologies of pharmaceutical intelligent manufacturing production line

1 Status of pharmaceutical equipment

Intelligent manufacturing process refers to the advanced manufacturing process that integrates the new generation of information technology such as the Internet of Things, big data and cloud computing with all aspects of manufacturing activities such as design, production, management and service, and has functions such as self-perception of information depth, intelligent optimization and self-decision making, precise control and self-execution [6]. Intelligent robots are committed to solving highly repeatable tasks, and the use of intelligent robots in the pharmaceutical process can not only independently complete the tasks from pharmaceutical to packaging process, but also effectively control the intensity of aseptic production, and achieve efficient production while ensuring that the quality of drugs meets the testing standards.

Although China's pharmaceutical equipment has been moving toward the goal of intelligence, the development speed is still slow. The pharmaceutical industry should seize the historical opportunity of intelligent development and step up the development of new, intelligent and integrated pharmaceutical equipment [7−8]. Many teams and enterprises at home and abroad have carried out in-depth research on the pharmaceutical intelligent manufacturing industry, and achieved certain results.

Wu Chengzhong et al. [9−13] developed a number of dispensing robots and medical quality inspection robots, and conducted in-depth research on vision inspection system and foreign body detection algorithm. In view of some adverse phenomena in the development of TCM intelligent manufacturing in current TCM enterprises, Cao Tingting et al. [14] built a theoretical model of TCM intelligent manufacturing from the basic concepts of flexible production and intelligent equipment, providing a reference for the realization of TCM intelligent manufacturing. Chutian Technology Co., Ltd. has also developed a number of intelligent robots such as intelligent handling robots, packaging robots and foreign object detection robots based on machine vision.

The Brevetti CEA Group also offers a comprehensive range of automated testing equipment for injectable medicines in multi-vial forms such as syringes, ampoules and large infusions to meet the needs of the pharmaceutical industry. In addition, companies such as Italy's Seidenader and Japan's Eisai have also played an important role in promoting the development of pharmaceutical intelligent manufacturing. Although the pharmaceutical equipment of the above enterprises provides an important guarantee for the rapid and safe production of drugs, a single pharmaceutical equipment will always bring some unavoidable problems. integrated continuous manufacturing (ICM) can connect multiple pharmaceutical processes into a production line through intelligent robots to realize a complete pharmaceutical process, which is of great significance for enhancing the scalability of the production process and shortening the time to market of new drugs [15].

In view of the urgent needs of the pharmaceutical industry, the research of pharmaceutical intelligent manufacturing production lines in line with the international pharmaceutical production quality Management practice (GMP) is an important guarantee for drug quality safety, bactericidal production and intelligent production. It can minimize the occurrence of drug safety accidents, improve the pharmaceutical manufacturing and production system, and protect people's health. At present, the existing technical difficulties in pharmaceutical intelligent manufacturing production lines include the following points.

1) The pharmaceutical technology and equipment process is complex, and the control of sterilization is difficult, which is reflected in: it is easy to mix impurities in the process of production process handover, thereby introducing foreign bodies; In the process of handling, it is difficult to ensure the sterile environment of drugs, which is easy to cause oxidation and deterioration of drugs; Manual involvement in the pharmaceutical process can also lead to contamination and the destruction of the sterile environment.

2) The pollution particles in the pharmaceutical process are small, diverse, and difficult to detect. The pollutants mixed in the pharmaceutical process include silk thread, transparent plastic, glass fragments, etc., which is difficult to identify manually and the detection effect is not good.

3) There are many types of medicine bottles, which are difficult to grasp flexibly and the handling efficiency is not high. Due to the different specifications of medicine bottles, the efficiency of manual handling of drugs is not high, and the flexible grasping of intelligent handling robots is difficult.

4) The collaborative control of multi-process, multi-task and multi-machine in high-end pharmaceutical process is difficult. The whole pharmaceutical process involves the application of multi-type intelligent robots, which is of great significance for improving pharmaceutical efficiency, but the application of multi-type robots also brings problems such as complex control scheme and difficult collaborative control.

To this end, with the continuous advancement of the pharmaceutical industry 4.0 era, the study of pharmaceutical intelligent manufacturing production line is the trend of The Times, through the combination of intelligent robots and intelligent manufacturing, the construction of integrated, automated intelligent manufacturing production line is an important topic of the pharmaceutical industry, so the study of highly sterile, intelligent pharmaceutical intelligent manufacturing production line is crucial.

2 Key technologies of pharmaceutical intelligent manufacturing production line

The pharmaceutical intelligent manufacturing production line proposed in this paper is an intelligent manufacturing system composed of multiple intelligent robots, such as sterile flexible dispensing robot, sterile filling-transaction-sealing robot, pharmaceutical quality visual inspection robot, sterile sorting and packaging robot, and intelligent handling robot, as shown in Figure 1. It can realize bacteria-free, automated drug production and packaging from pharmaceutical process to packaging process.

As a representative advanced pharmaceutical production line in the field of pharmaceutical equipment manufacturing, it is necessary to study its key technologies. This paper mainly focuses on the key technologies such as inbacterialized intelligent production, visual inspection of medical quality, flexible grasping and intelligent handling, and intelligent coordination and optimization control. Combined with the research results of our own team and domestic and foreign scholars, the research progress is described and analyzed.

2.1 Bactericidal intelligent production

The sterilization operation of pharmaceutical production covers the production environment, packaging materials, drugs themselves and other aspects, and the sterilization process always runs through the beginning and end of the production process. However, the current asphyxiation technology is limited by many factors such as drug types and pharmaceutical processes, and the asphyxiation of pharmaceutical processes has always been an international technical problem in urgent need of breakthroughs [16].

Because the traditional sterilization technology mainly relies on the high temperature sterilization of drugs, it is difficult to meet the sterilization standard of drugs on the one hand, and it is difficult to avoid the secondary pollution of drugs after sterilization. For this reason, JILDEH et al. [17] tried to develop a new sterilization process using hydrogen peroxide, and analyzed and verified it through numerical simulation. The use of supercritical carbon dioxide for sterilization is a green and sustainable technology.

RIBEIRO et al. [18] studied the experimental method of supercritical sterilization and evaluated its effect and application in medicine. In addition, PREEM et al. [19] evaluated the effects of various sterilization methods, such as gamma ray irradiation, ultraviolet irradiation, in-situ generation of chlorine gas and low argon plasma treatment, and studied the changes in drug stability, morphology and other drug properties before and after sterilization. As the selection and evaluation of sterilization process is an important topic for realizing bactericidal intelligent production, SHIRAHATA et al. [20] developed an online decision support tool for the selection of aseptic filling technology in biopharmaceutical production. In addition, ARREOLA et al. [21] proposed a combined biosensor array based on calorimetric gas and spores to monitor and evaluate the germicidal effect of hydrogen peroxide gas in aseptic filling machines.

In this process, the separation of the bottle embryo manufacturing and the subsequent process will lead to the adsorption of bacteria and suspended particles in the air on the drug, thus causing the packaging material to be polluted. Therefore, it is necessary to achieve ultra-clean blowing and sealing in the same mold. In the production line of blowing, filling and sealing of plastic ampoules, a sealed vacuum system and aseptic air flow control were adopted to build a complex electromechanical, temperature, gas and hydraulic control system to realize a new process and principle of blowing, filling and sealing of plastic injection, so as to develop an integrated blowing, filling and sealing pharmaceutical machine to meet the whole process of bacteria-free production of drugs in the same mold.

2.2 Visual inspection of medical quality

The visual inspection of medical quality mainly includes the detection of visible foreign bodies in medicine, the detection of components and the detection of packaging defects. Traditional medical quality detection is mainly through artificial naked eye detection, because the human eye is easy to fatigue, easy to be affected by external interference, easy to lead to missed detection, false detection, resulting in poor product quality, low production efficiency. Therefore, it is very important to develop a visual inspection robot for the quality inspection of oral liquid, ampoule, infusion bottle and other liquid products on the pharmaceutical production line. The pharmaceutical quality visual inspection robot can detect the glass debris, aluminum debris, rubber shavings, hair, fiber and other foreign bodies in the pharmaceutical liquid online, identify the damage of the bottle itself, the packaging quality of the bottle mouth and other defects, and can automatically sort unqualified products.

In the development process of visual robot for medical quality inspection, the existing visual foreign body detection methods are difficult to meet the requirements of online detection of weak medical foreign bodies with various types, diverse features and high speed and accuracy. Therefore, the mechanical structure design of the medical quality visual inspection robot, image acquisition of weak foreign body targets under complex background, visual detection and recognition and other technologies are studied. It is the key and difficult point of medical quality visual inspection robot.

2.2.1 Mechanical structure

The mechanical structure of pharmaceutical quality visual inspection robot is directly related to the performance of drug image acquisition and detection methods, and its scientificity and rationality are particularly important.

At the same time, the moving parts can be integrated and analyzed in the digital environment to solve the kinematic constraint equation between the moving mechanism, and the simulation operation, process optimization, spatial interference analysis, collision analysis and other experiments can be carried out on the integrated digital platform, and finally the structure can be improved and optimized according to the experimental results. The whole mechanism of the robot can be analyzed from the aspects of design, processing, material, assembly and so on, with high precision, high symmetry, dynamic balance and global stability during operation. Then, according to the changeable packaging forms and specifications of drugs, the body structure of multi-type pharmaceutical foreign body visual detection robot is designed, which can realize the detection of different specifications and models of pharmaceutical products.

Service coordination control system

The drug image acquisition system not only directly affects the quality of the image, but also indirectly affects the performance of the detection algorithm. Therefore, for the weak foreign object image acquisition scheme under complex background, a series of repetitive action commands such as "precise alignment - flexible bottle grab - high-speed rotation - emergency stop - image acquisition - foreign object detection - sorting" are usually executed by the manipulator, and then the image is acquired by the CCD camera.

In this process, due to the existence of mechanical vibration, the camera will be inaccurate in focusing and the obtained medical detection image will be blurred, which will increase the false alarm rate of detection. In addition, with the increasing production demand, the pharmaceutical industry has put forward a higher demand for the speed of medical quality detection, and a single CCD camera is difficult to meet this requirement. In the multi-manipulator visual servo cooperative control system, by setting several high-resolution image sensors on the single tracking swing arm and optimizing the control time sequence of rotation-stop-tracking shooting, both high-resolution and stable images can be obtained and the detection speed can be improved. By optimizing the variable control parameters such as bottle clamping, bottle rolling and speed, the manipulator can simulate the effect of human bottle rolling in a fast and smooth mode, and improve the stability of bottle rotation.

Through the use of distributed network intelligent control system of vision inspection robot, including multi-channel vision sensor image acquisition and processing, multi-channel robot bottle clamping and bottle rolling optimization control, product classification and packaging control, etc., the opto-electromechanical system can ensure the coordinated work.

2.2.3 Visual detection and recognition algorithm

In the complex pharmaceutical production process, the occurrence of drug quality defects such as foreign bodies and packaging damage is unavoidable. Foreign bodies will directly affect the therapeutic effect of drugs, and even threaten the health of patients. Packaging damage can also directly damage the sterile environment of the drug and indirectly affect the quality of the drug. Therefore, visual detection and recognition technology is very important in the medical quality inspection.

Foreign bodies usually refer to some weak foreign bodies that are not obvious, such as silk thread, transparent plastic, glass fragments, etc., whose images have the characteristics of low contrast and low energy. Since foreign objects are small in size and most of them are transparent, the grayscale of the actual image does not change much relative to surrounding pixels, and the contour is fuzzy. In addition, external noise interference also makes the entire foreign object detection process more difficult. Therefore, in complex environments, research on detection and recognition methods with strong anti-interference and high robustness is the key to solve the problem of tiny target detection. It can greatly reduce the system error rate. Traditional methods usually filter, segment, edge extraction and other operations on the original image of foreign bodies, then select appropriate feature parameters, and finally classify and recognize foreign bodies through classification algorithms.

GE et al. modeled the moving target in the liquid medicine, combined with the acquired sequence frame images to achieve feature extraction of the foreign object, and finally proposed the online sequential extreme learning machine (OS-ELM) based on space. Thus the classification of foreign bodies in liquid medicine is realized. In addition, ZHANG et al. [22] proposed a particle tracking and classification algorithm based on the adaptive local weighted collaborative sparse model (ALW-CSM). An automatic liquid particle detection system for injection is designed, which has better performance than OS-ELM algorithm. Aiming at the interference of bubbles on the detection of visible foreign bodies, Wang Yuqing et al. [24] proposed to take the region of interest of image sequence as the object. Firstly, using frame difference method, the image most likely to contain foreign bodies in image sequence was found as the start frame image, and the moving object in the start frame image was found to establish the initial template. Then, ECO(efficiency convolution operators) algorithm is used to track the moving target, record its trajectory and analyze its motion characteristics, so as to identify whether the target is a foreign body.