Search

The unprecedented prosperity of the industrial internet of things (IIoT) has opened up a new path for the traditional industrial manufacturing model.Intelligent shop scheduling is one of the key technologies to achieve the overall control and flexible production of the whole production process.It requires an effective plan with a minimum makespan to allocate multiple processes and multiple machines for production scheduling.Firstly, the shop scheduling problem was defined as a Markov decision process (MDP), and a shop scheduling model based on the pointer network was established.Secondly, the job scheduling process was regarded as a mapping from one sequence to another, and a new shop scheduling algorithm based on deep reinforcement learning (DRL) was proposed.By analyzing the convergence of the model under different parameter settings, the optimal parameters were determined.Experimental results on different scales of public data sets and actual production data sets show that the proposed DRL algorithm can obtain better performances.

Industry 4.0 relates to the digital revolution of manufacturing and other sectors, such as retail, distribution, oil and gas, and infrastructure. Meanwhile, the Industrial Internet of Things (IIoT) is a technological advancement that leads to Industry 4.0 implementation by boosting the manufacturing sector’s productivity and economic impact. IIoT provides the ability to provide global connectivity between components in different locations. The manufacturing sector has had various difficulties implementing IIoT, primarily due to IIoT characteristics. This paper offers an in-depth review of Industry 4.0 and IIoT, where the primary motivation behind this is to introduce the most recent advancements related to Industry 4.0 and IIoT, as well as to address the existing limitations. Firstly, this paper presents a novel taxonomy of IIoT challenges that includes aspects of each challenge, such as the terminology and approaches utilized to solve these challenges. Besides IIoT challenges, this survey provides an in-depth demonstration of the many concepts related to IIoT, such as architecture and use cases. Secondly, this paper provides a comprehensive review of the state-of-the-art of Industry 4.0 in terms of concepts, requirements, and supporting technology. In addition, the correlation between enabling technology and technical requirements is discussed in detail. Finally, this paper highlights deep learning, edge computing, and big data as key techniques for the future directions of IIoT. Furthermore, the presented techniques are thoroughly examined to present an alternative method for future adoption. In addition to the showcased techniques, a new architecture for the future of IIoT based on these three primary techniques is also proposed.

Significant advancements in contemporary telemedicine applications enforce the demand for effective and intuitive telerehabilitation tools. Telerehabilitation can minimize the distance, travel burden, and costs between rehabilitative patients and therapists. This research introduces an interactive novel telerehabilitation system that integrates the Industrial Internet of Things (IIoT) platform with a robotic manipulator named xARm-5, aiming to deliver rehabilitation therapies to individuals with upper limb dysfunctions. With the proposed system, a therapist can provide upper limb rehab exercises remotely using an augmented reality (AR) user interface (UI) developed using Vuforia Studio, which transmits bidirectional data through the IIoT platform. The proposed system has a stable communication architecture and low teleoperation latency. Experimental results revealed that with the developed telerehabilitation framework, the xArm-5 could be teleoperated from the developed AR platform and/or use a joystick to provide standard upper limb rehab exercises. Besides, with the designed AR-based UI, a therapist can monitor rehab/robot trajectories along with the AR digital twin of the robot, ensuring that the robot is providing passive therapy for shoulder and elbow movements.

It has been proven that Internet of Things (IoT) platforms can improve the performance and efficiency of a wide range of processes. With the acceptance of IoT as a major part of the technology of Industry 4.0, the notion of leveraging the Internet in industries to enable automation and reconfigure existing industrial processes has greatly evolved. By introducing smart technology and intelligent processes, the Industrial Internet of Things (IIoT) is committed to bringing high operational efficiency, enhanced productivity, and effective management to industrial assets. Despite this, the reliance of IIoT on central architecture presents numerous challenges, including the security and maintenance of smart devices, privacy issues owing to third-party participation, and massive computations conducted by a central entity, all of which prevent its widespread adoption in businesses. Emerging blockchain technologies have the potential to transform IIoT platforms and applications. A distributed and decentralized approach followed by blockchain might offer interesting solutions to the challenges raised by IIoT. Furthermore, 5G networks are expected to deliver excellent solutions to meet the demands of decentralized systems, with a focus on application-specific vulnerabilities. Blockchain and IIoT, enabled by 5G, is a viable option to fully explore the potential of contemporary industry. In this context, this article analyzes and examines recent achievements to highlight the major obstacles in blockchain–IIoT convergence and presents a framework for potential solutions. A well-organized literature review by analyzing the existing work in three primary areas: blockchain consensus algorithms used in existing IoT and IIoT applications, blockchain for 5G-enabled IoT networks, and blockchain in industry have been performed, with major findings summarized in each area. Directions for the future are also provided and intend to assist researchers in understanding the full potential of these innovations.

This work introduces a scalable, cloud-agnostic and fault-tolerant data analytics platform for state-of-the-art autonomous systems that is built from open-source, reusable building blocks. As the baseline for further new reference architectures, it represents an architecture blueprint for processing, enriching and analyzing various feeds of structured and non-structured input data from advanced Internet-of-Things (IoT) based use cases. The platform builds on industry best practices, leverages on solid open-source components in a reusable fashion, and is based on our experience gathered from numerous IoT and Big Data research projects. The platform is currently used in the framework of the National Laboratory for Autonomous Systems in Hungary (abbreviated as ARNL). The platform is demonstrated through selected use cases from ARNL including the areas of smart/autonomous production systems (collaborative robotic assembly) and autonomous vehicles (mobile robots with smart vehicle control). Finally, we validate the platform through the evaluation of its streaming ingestion capabilities.

Предметом дослідження є можливі засоби підвищення апаратної безпеки кінцевих пристроїв туманних обчислень в мережах Інтернету речей (ІоТ), популярність якого щороку стрімко зростає та потребує високого рівня захищеності від усіх типів атак. Метою роботи є огляд доступних готових комерційних продуктів та/або концептуальних апаратних рішень для захисту бюджетних пристроїв у мережах Інтернету речей на основі туманних технологій. Для досягнення поставленої мети виконано такі завдання: запропоновано концепцію туманних обчислень та визначено переваги, які вона надає мережам IoT; розглянуто кіберзагрози та апаратні атаки на мережі ІоТ; описано наслідки використання мереж Інтернету речей на основі туманних обчислень; розглянуто апаратні засоби безпеки, такі як TRM, PUF, HSM тощо. Для вирішення завдань використано такі методи дослідження, як: теоретичний аналіз літературних джерел; порівняльний аналіз хмарних, туманних і мобільних обчислень; аналіз наявних апаратних засобів безпеки. Здобуто такі результати: туманні обчислення можна розглядати як шлюз між хмарними обчисленнями та Інтернетом речей; вони мають більшість із переваг хмарних обчислень, крім того, додатково дають змогу обробляти дані на кінцевих пристроях, не навантажуючи центральний сервер. Висновки: безпека апаратного забезпечення в системах Інтернету речей не менш важлива, ніж програмна безпека. Особливо вагомо це питання постає для систем на основі туманних обчислень, де дані оброблятимуться на периферії, без передачі в хмару. Для підвищення рівня апаратної безпеки пристроїв туманних обчислень пропонується використовувати стандартні апаратні платформи безпеки, такі як: фізично неклоновані функції, апаратний модуль безпеки, система на кристалі тощо. Апаратні компоненти системи, що застосовують туманні обчислення, менш схильні до кібератак, зломів, вторгнень чи маніпуляцій.

The Industrial Internet of Things (IIoT) incorporates intelligent computing and artificial intelligence paradigms in smart factories for ease of production and human-less interventions. The controlling unit is integrated into the smart operations in managing, controlling, and monitoring industrial operations. This article introduces an Operation-Constrained Process Control (OCPC) for preventing time-lag errors between smart machine operation cycles. The proposed method considers the operational cycles, completion time, and output efficiency metrics for identifying time lags and errors in production. Depending on the maximum productivity-based outcomes, further allocations or modifications in the regular operational cycles are identified. The productivity is analyzed based on the previous outcomes using federated learning. This learning implies multi-sensor knowledge update and production efficiency through repeated training. Therefore, the errors in cycle assignment and production completion are synchronized under controlled error. This method is analyzed using time lag, error, production efficiency, and training instances.

The Internet of Things (IoT) ecosystem has proliferated based on the use of the internet and cloud-based technologies in the industrial area. IoT technology used in the industry has become a large-scale network based on the increasing amount of data and number of devices. Industrial IoT (IIoT) networks are intrinsically unprotected against cyber threats and intrusions. It is, therefore, significant to develop Intrusion Detection Systems (IDS) in order to ensure the security of the IIoT networks. Three different models were proposed to detect intrusions in the IIoT network by using deep learning architectures of Convolutional Neural Network (CNN), Long Short Term Memory (LSTM), and CNN + LSTM generated from a hybrid combination of these. In the study conducted by using the UNSW-NB15 and X-IIoTID datasets, normal and abnormal data were determined and compared with other studies in the literature following a binary and multi-class classification. The hybrid CNN + LSTM model attained the highest accuracy value for intrusion detection in both datasets among the proposed models. The proposed CNN + LSTM architecture attained an accuracy of 93.21% for binary classification and 92.9% for multi-class classification in the UNSW-NB15 dataset while the same model attained a detection accuracy of 99.84% for binary classification and 99.80% for multi-class classification in the X-IIoTID dataset. In addition, the accurate detection success of the implemented models regarding the types of attacks within the datasets was evaluated.

In this study, an industrial internet of things (IIoT) based sensor card system has been developed to predict the failures that may occur in induction motors (IMs), which is widely used in the industry and therefore it is important to take predictive maintenance measures. The realized system has been tested on a 3-phase IM with 250 kW power and 315L body structure. The conditions of this IM were detected by the sensors in the embedded system and transferred to a cloud network with the embedded system. The ESP-WROOM-32 microcontroller, which includes Wi-Fi and Bluetooth communication protocols in the sensor card application, is mounted on a LIS3DH accelerometer that detects frequency-dependent vibration data in three axes and NTC IM at 10 KQ for temperature data. By evaluating these sensor data, predictive maintenance determinations that may occur in the IM were made and predictive maintenance decisions were made for the IM to send warnings to the users with these detections. [ABSTRACT FROM AUTHOR]

The research and development (R&D) of the scale-up process of third-generation photovoltaics (PVs) can benefit from the emerging trends and technologies related to the Industrial Internet of Things. However, to migrate the small-scale laboratory PVs products to a larger version of the industrial scale, a processing platform is needed to design, fabricate, and test the production line. In this paper, after a brief introduction of the production process of thin-film PVs, specifically dye-sensitized solar cells, the Industrial Internet Reference Architecture (IIRA) has been applied to the R&D scenario for the production of thin-film PVs, in order to synchronize and manage the large amount of data generated by the real, virtual or hybrid production devices and processes. The results of this study suggest that the future implementation of IIRA is a reliable option in a learning factory environment for multidisciplinary collaboration, research training in novel technologies and methods in the Tijuana Institute of Technology. This contribution is in order to optimize and scale-up the production process of a new generation of solar cells. [ABSTRACT FROM AUTHOR]

With the continuous maturity of the fifth generation (5G) communications, industrial Internet of Things (IIoT) technology has been widely applied in fields such as smart factories. In smart factories, 5G-based production line monitoring can improve production efficiency and reduce costs, but there are problems with limited monitoring coverage and insufficient wireless spectrum resources, which restricts the application of IIoT in the construction of smart factories. In response to these problems, we propose a hybrid spectrum access mechanism based on Non-OrthogonalMultiple Access (NOMA) cooperative relaying transmission to improve the monitoring coverage and spectrum efficiency. As there are a large number of production lines that need to be monitored in smart factories, it is difficult to realize real-time monitoring of all production lines due to insufficient wireless resources. Therefore, we divide the production lines into high priority and low priority, and introduce cognitive radio technology to increase the number of monitoring production lines. In order to better describe the wireless fading channel environment in the factory, the two-wave with diffuse power (TWDP) channel is discussed to simulate the real factory environment and the outage probability of the secondary production line data transmission is derived in the proposed mechanism. Compared with the traditional mechanism, the proposed transmission mechanism can ensure the continuity of the secondary transmission, greatly reduce the outage probability of the secondary transmission, and improve the efficiency of the monitoring of the production lines. [ABSTRACT FROM AUTHOR]

The rapid development in manufacturing industries due to the introduction of IIoT devices has led to the emergence of Industry 4.0 which results in an industry with intelligence, increased efficiency and reduction in the cost of manufacturing. However, the introduction of IIoT devices opens up the door for a variety of cyber threats in smart industries. The detection of cyber threats against such extensive, complex, and heterogeneous smart manufacturing industries is very challenging due to the lack of sufficient attack traces. Therefore, in this work, a Federated Learning enabled Deep Intrusion Detection framework is proposed to detect cyber threats in smart manufacturing industries. The proposed FLDID framework allows multiple smart manufacturing industries to build a collaborative model to detect threats and overcome the limited attack example problem with individual industries. Moreover, to ensure the privacy of model gradients, Paillier-based encryption is used in communication between edge devices (representative of smart industries) and the server. The deep learning-based hybrid model, which consists of a Convolutional Neural Network, Long Short Term Memory, and Multi-Layer Perceptron is used in the intrusion detection model. An exhaustive set of experiments on the publically available dataset proves the effectiveness of the proposed framework for detecting cyber threats in smart industries over the state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

While many companies worldwide are still striving to adjust to Industry 4.0 principles, the transition to Industry 5.0 is already underway. Under such a paradigm, Cyber-Physical Human-centered Systems (CPHSs) have emerged to leverage operator capabilities in order to meet the goals of complex manufacturing systems towards human-centricity, resilience and sustainability. This article first describes the essential concepts for the development of Industry 5.0 CPHSs and then analyzes the latest CPHSs, identifying their main design requirements and key implementation components. Moreover, the major challenges for the development of such CPHSs are outlined. Next, to illustrate the previously described concepts, a real-world Industry 5.0 CPHS is presented. Such a CPHS enables increased operator safety and operation tracking in manufacturing processes that rely on collaborative robots and heavy machinery. Specifically, the proposed use case consists of a workshop where a smarter use of resources is required, and human proximity detection determines when machinery should be working or not in order to avoid incidents or accidents involving such machinery. The proposed CPHS makes use of a hybrid edge computing architecture with smart mist computing nodes that processes thermal images and reacts to prevent industrial safety issues. The performed experiments show that, in the selected real-world scenario, the developed CPHS algorithms are able to detect human presence with low-power devices (with a Raspberry Pi 3B) in a fast and accurate way (in less than 10 ms with a 97.04% accuracy), thus being an effective solution (e.g., a good trade-off between cost, accuracy, resilience and computational efficiency) that can be integrated into many Industry 5.0 applications. Finally, this article provides specific guidelines that will help future developers and managers to overcome the challenges that will arise when deploying the next generation of CPHSs for smart and sustainable manufacturing. [ABSTRACT FROM AUTHOR]

• A fast and efficient cyberattack detection scheme is introduced to enhance the security and trustworthiness of an IIoT system by using a Deep Random Neural Network (DRaNN). • A hybrid particle swarm optimization (PSO) with sequential quadratic programming (SQP) is incorporated for optimal training of DRaNN. • The proposed scheme is evaluated and its effectiveness is verified in both binary class and multiclass scenarios by using three newly reported IIoT datasets DS2OS, UNSW-NB15 and ToN_IoT. The Industrial Internet of Things (IIoT) is a rapidly emerging technology that increases the efficiency and productivity of industrial environments by integrating smart sensors and devices with the internet. The advancements in communication technologies have introduced stable connectivity and a higher data transfer rate in the IIoT. The IIoT devices generate a massive amount of information that requires intelligent data processing techniques for the development of cybersecurity mechanisms. In this regard, deep learning (DL) can be an appropriate choice. This paper proposes a Deep Random Neural Network (DRaNN) based fast and reliable attack detection scheme for IIoT environments. The RaNN is an advanced variant of the traditional Artificial Neural Network (ANN) with a highly distributed nature and better generalization capabilities. To attain a higher attack detection accuracy, the proposed RaNN is optimally trained by incorporating hybrid particle swarm optimization (PSO) with sequential quadratic programming (SQP). The SQP-enabled PSO facilitates the neural network to select optimal hyperparameters. The efficacy of the suggested scheme is analyzed in both binary and multiclass configurations by conducting extensive experiments on three new IIoT datasets. The experimental outcomes demonstrates the promising performance of the proposed design for all datasets. [ABSTRACT FROM AUTHOR]

Sensors are the foundational components of any smart machine system and are invaluable in all modern technologies. Consequently, faults and errors in sensors can have a significant negative impact on the setup. Intelligent, lightweight, and accurate fault diagnosis and mitigation lie at the crux of modern industries. This study aimed to conceptualize a germane solution in the domain of fault detection, focusing on Hall-effect rotary encoders. Position monitoring through rotary encoders is essential to the safety and seamless functioning of industrial equipment such as lifts and hoists, and commercial systems such as automobiles. This work used multi-strategy learners to accurately diagnose quadrature and offset faults in Hall-effect rotary encoders. The obtained dataset was then run through a lightweight ensemble classifier to train a robust fault detection model. The complete mechanism was simulated through interconnected models simulated in a MATLAB Simulink™ environment. In real time, the developed fault detection algorithm was embedded in an FPGA controller and tested with a 1 kW PMSM drive system. The resulting system is computationally inexpensive and achieves an accuracy of 95.8%, making it a feasible solution for industrial implementation. [ABSTRACT FROM AUTHOR]

The Zero Trust concept is being adopted in information technology (IT) deployments, while human users remain to be the main risk for operational technology (OT) deployments. This article proposes to enhance the new Modbus/TCP Security protocol with authentication and authorization functions that guarantee security against intentional unauthorized access. It aims to comply with the principle of never trusting the person who is accessing the network before carrying out a security check. Two functions are tested and used in order to build an access control method that is based on a username and a password for human users with knowledge of industrial automation control systems (IACS), using simple means, low motivation, and few resources. A man-in-the-middle (MITM) component was added in order to intermediate the client and the server communication and to validate these functions. The proposed scenario was implemented using the Node-RED programming platform. The tests implementing the functions and the access control method through the Node-RED software have proven their potential and their applicability. [ABSTRACT FROM AUTHOR]

The IEEE 802.15.4 Time Slotted Channel Hopping (TSCH) communication mode is a key standard in the Industrial Internet of Things (IIoT). To schedule communications, TSCH uses deterministic transmissions to deal with latency requirements and channel hopping to cope with interference in IIoT environments. Nonetheless, this latter might not be sufficient to ensure reliable delivery of critical data since industrial networks are prone to severe external interference, which impacts the quality of wireless channels. In this paper, we propose an effective local Channel Selection approach for Reliable communication Scheduling in TSCH networks, dubbed CSRS. CSRS leans on effective assessment metrics to estimate the quality of available communication channels and stateless local exchange of bad-channels blacklists. CSRS is schedule-independent; hence it can be combined with any TSCH schedule, including the standardized Minimal Scheduling Function (MSF), to reduce the negative impact of bad channels. CSRS integration with MSF is implemented in Contiki and validated through extensive realistic trace-based simulations and public testbed experiments. Obtained results demonstrate the efficiency of our proposal in terms of reliability, latency, and energy consumption when compared with state-of-the-art solutions. [ABSTRACT FROM AUTHOR]

The development of 5G networks has rapidly increased the use of Industrial Internet of Things (IIoT) devices for control, monitoring, and processing purposes. Biometric-based user authentication can prevent unauthorized access to IIoT devices, thereby safeguarding data security during production. However, most biometric authentication systems in the IIoT have no template protection, thus risking raw biometric data stored as templates in central databases or IIoT devices. Moreover, traditional biometric authentication faces slow, limited database holding capacity and data transmission problems. To address these issues, in this paper we propose a secure online fingerprint authentication system for IIoT devices over 5G networks. The core of the proposed system is the design of a cancelable fingerprint template, which protects original minutia features and provides privacy and security guarantee for both entity users and the message content transmitted between IIoT devices and the cloud server via 5G networks.Compared with state-of-the-art methods, the proposed authentication system shows competitive performance on six public fingerprint databases, while saving computational costs and achieving fast online matching. [ABSTRACT FROM AUTHOR]

With the development of the Industrial Internet of Things (IIoT), industrial wireless sensors need to upload the collected private data to the cloud servers, resulting in a large amount of private data being exposed on the Internet. Private data are vulnerable to hacking. Many complex wireless-sensor-authentication protocols have been proposed. In this paper, we proposed an efficient authentication protocol for IIoT-oriented wireless sensor networks. The protocol introduces the PUF chip, and uses the Bloom filter to save and query the challenge–response pairs generated by the PUF chip. It ensures the security of the physical layer of the device and reduces the computing cost and communication cost of the wireless sensor side. The protocol introduces a pre-authentication mechanism to achieve continuous authentication between the gateway and the cloud server. The overall computational cost of the protocol is reduced. Formal security analysis and informal security analysis proved that our proposed protocol has more security features. We implemented various security primitives using the MIRACL cryptographic library and GMP large number library. Our proposed protocol was compared in-depth with related work. Detailed experiments show that our proposed protocol significantly reduces the computational cost and communication cost on the wireless sensor side and the overall computational cost of the protocol. [ABSTRACT FROM AUTHOR]

The core of the research focuses on analyzing the discharge characteristic of a lithium NMC battery in an autonomous mobile robot, which can be used as a model to predict its future states depending on the amount of missions queued. In the presented practical example, an autonomous mobile robot is used for in-house transportation, where its missions are queued or delegated to other robots in the system depending on the robots' predicted state of charge. The system with the implemented models has been tested in three scenarios, simulating real-life use cases, and has been examined in the context of the number of missions executed in total. The main finding of the research is that the battery discharge characteristic stays consistent regardless of the mission type or length, making it usable as a model for the predictive monitoring system, which allows for detection of obstruction of the default shortest paths for the programmed missions. The model is used to aid the maintenance department with information on any anomalies detected in the robot's path or the behavior of the battery, making the transportation process safer and more efficient by alerting the employees to take action or delegate the excessive tasks to other robots. [ABSTRACT FROM AUTHOR]

The rapid technological advances of cellular technologies will revolutionize network automation in industrial internet of things (IIoT). In this paper, we investigate the two-timescale resource allocation problem in IIoT networks with hybrid energy supply, where temporal variations of energy harvesting (EH), electricity price, channel state, and data arrival exhibit different granularity. The formulated problem consists of energy management at a large timescale, as well as rate control, channel selection, and power allocation at a small timescale. To address this challenge, we develop an online solution to guarantee bounded performance deviation with only causal information. Specifically, Lyapunov optimization is leveraged to transform the long-term stochastic optimization problem into a series of short-term deterministic optimization problems. Then, a low-complexity rate control algorithm is developed based on alternating direction method of multipliers (ADMM), which accelerates the convergence speed via the decomposition-coordination approach. Next, the joint channel selection and power allocation problem is transformed into a one-to-many matching problem, and solved by the proposed price-based matching with quota restriction. Finally, the proposed algorithm is verified through simulations under various system configurations. [ABSTRACT FROM AUTHOR]

Biosensors-based devices are transforming medical diagnosis of diseases and monitoring of patient signals. The development of smart and automated molecular diagnostic tools equipped with biomedical big data analysis, cloud computing and medical artificial intelligence can be an ideal approach for the detection and monitoring of diseases, precise therapy, and storage of data over the cloud for supportive decisions. This review focused on the use of machine learning approaches for the development of futuristic CRISPR-biosensors based on microchips and the use of Internet of Things for wireless transmission of signals over the cloud for support decision making. The present review also discussed the discovery of CRISPR, its usage as a gene editing tool, and the CRISPR-based biosensors with high sensitivity of Attomolar (10−18M), Femtomolar (10−15M) and Picomolar (10−12M) in comparison to conventional biosensors with sensitivity of nanomolar 10−9M and micromolar 10−3M. Additionally, the review also outlines limitations and open research issues in the current state of CRISPR-based biosensing applications. [ABSTRACT FROM AUTHOR]

The integration of smart devices in the manufacturing section has brought along disruptions in the production processes. The existing literature in the field of IIoT and Industry 4.0 have focused much on the technical aspects of the network design and development, however, there is a substantial gap in examining the challenges of implementation of IIoT techniques, especially in context to India. This paper presents an exhaustive analysis and categorization of the challenges faced by the manufacturing sector in the implementation of the Industrial Internet of Things (IIoT). Challenges were categorized into technical and organizational challenges with the help of experts. The paper aims to attain a hierarchical structure, which will further be helpful to policymakers to identify the most critical challenge allowing them to make a well-versed decision. The results of this study are expected to highlight the key challenge wherein the industry and researchers can focus their strategic efforts. This will facilitate the address of implicit issues while implementing IIoT Techniques in the manufacturing industry. [ABSTRACT FROM AUTHOR]

In recent years, with the application of Internet of Things (IoT) and cloud technology in smart industrialization, Industrial Internet of Things (IIoT) has become an emerging hot topic. The increasing amount of data and device numbers in IIoT poses significant challenges to its security issues, making anomaly detection particularly important. Existing methods for anomaly detection in the IIoT often fall short when dealing with data imbalance, and the huge amount of IIoT data makes feature selection challenging and computationally intensive. In this paper, we propose an optimal deep learning model for anomaly detection in IIoT. Firstly, by setting different thresholds of eXtreme Gradient Boosting (XGBoost) for feature selection, features with importance above the given threshold are retained, while those below are ignored. Different thresholds yield different numbers of features. This approach not only secures effective features but also reduces the feature dimensionality, thereby decreasing the consumption of computational resources. Secondly, an optimized loss function is designed to study its impact on model performance in terms of handling imbalanced data, highly similar categories, and model training. We select the optimal threshold and loss function, which are part of our optimal model, by comparing metrics such as accuracy, precision, recall, False Alarm Rate (FAR), Area Under the Receiver Operating Characteristic Curve (AUC-ROC), and Area Under the Precision-Recall Curve (AUC-PR) values. Finally, combining the optimal threshold and loss function, we propose a model named MIX_LSTM for anomaly detection in IIoT. Experiments are conducted using the UNSW-NB15 and NSL-KDD datasets. The proposed MIX_LSTM model can achieve 0.084 FAR, 0.984 AUC-ROC, and 0.988 AUC-PR values in the binary anomaly detection experiment on the UNSW-NB15 dataset. In the NSL-KDD dataset, it can achieve 0.028 FAR, 0.967 AUC-ROC, and 0.962 AUC-PR values. By comparing the evaluation indicators, the model shows good performance in detecting abnormal attacks in the Industrial Internet of Things compared with traditional deep learning models, machine learning models and existing technologies., (© 2024. The Author(s).)