Indoor localization technology is essential for enabling location-based services (LBS). Millimeter-wave (mmWave) radar offers the potential for high-precision LBS; however, accurately localizing stationary individuals or those located behind obstacles remains a challenge due to the weakness and susceptibility of crucial echo signals. We propose a feasible scheme for locating motionless human in indoor through-wall nonline-of-sight (NLOS) scenarios, named LoMo, which infers accurate locations of a target from physiological signals. To achieve this goal, we design a coherent accumulation method to improve the target signal-to-noise ratio and strengthen the expression of weak signals. Then, we troubleshoot the coherent multipath problem by introducing an enhanced super-resolution algorithm with Toeplitz reconstruction of the covariance matrix, which enables the accurate separation of location-related signals. Finally, to avoid the ambiguity caused by diverse environmental variables, we present an adaptive clustering method for mmWave point clouds that considers the spatial features of the scene, allowing the obtaining of real location information without intensive manual effort. To validate the feasibility of LoMo, we run extensive experiments covering human diversity, orientations, and obstacle types. Experimental results show that LoMo achieves a localization error within 17 cm, and a correct identification rate of 96.1% within +/- 30 cm under through-wall NLOS conditions, outperforming state-of-the-art methods in comparison.

HVAC systems represent the primary energy consumption end-use in buildings. The operational status of HVAC systems directly impacts occupants' thermal comfort. Currently, reinforcement learning-based (RL) methods are widely applied to optimize HVAC system operation strategies. However, constrained by fixed task training mechanisms, traditional RL methods suffer from catastrophic forgetting when confronted with the diverse tasks encountered in real-world HVAC system operation scenarios. The continual reinforcement learning (CRL) based HVAC system optimization strategy was employed in this work to overcome the catastrophic forgetting challenge in RL. This paper employed a continual strategy updating module within the CRL framework, comprising experiences replay unit and task updating unit. It preserves high-reward experiences and their reuse while evaluating and balancing diverse tasks. Based on this approach, the air conditioning system optimization model effectively avoids catastrophic forgetting and adapts to varied tasks. The experimental results show that, compared to the baseline method, the CRL method performs better in terms of metrics such as violation rate, thermal comfort, energy consumption loss and incentive value.

The accurate prediction of building energy consumption provides technology and data support for the construction of intelligent building energy systems. Moreover, it is also a crucial means of responding to the national "Carbon Peaking and Carbon Neutrality Goals." Traditional methods can yield poor results because they fail to consider the nonlinear, nonstationary, and multi-seasonal characteristics of the building energy consumption data. To overcome these limitations, this paper proposes an asymmetric energy consumption prediction approach based on the encoder-decoder architecture. The proposed approach employs the CEEMDAN algorithm for data preprocessing to enhance the reliability of building energy consumption data. Subsequently, the convolutional gated recurrent unit (Conv-GRU) model is utilized to extract high-dimensional features and capture nonlinear relationships from the input energy consumption data. Finally, by employing the GRU-Attention algorithm to assign feature weights, this approach enhances the accuracy of building energy consumption prediction. Experimental evaluations conducted on real datasets demonstrate the superiority of the proposed approach over the existing classic methods.

The effective operation of sensors in heating, ventilation and air conditioning (HVAC) systems to promote high-efficiency, energy-saving and low-risk intelligent buildings. However, most existing methods are either based on a centralized architecture or employ only pure digital simulation platforms for HVAC sensor fault diagnosis and verification, which are difficult to meet the complex and dynamic needs of HVCA systems. To overcome the difficulty in employment of centralized architecture involved multi sensor fault diagnosis and fault diagnosis methods limited by pure digital simulation platform, a fully distributed chaotic bat algorithm is proposed to diagnosis multiple-sensor faults and is verified by the hardware-in-the-loop simulation platform in HVAC systems. First, inspired by the bat swarm intelligence and multiple agents, we characterize the sensor fault diagnosis problem as an optimization problem of the bat predation behavior. Specifically, each sensor node is abstracted as a bat colony, and each bat colony communicates with directly connected neighboring bat colony in physical space. Second, to avoid the tendency of bat algorithm to fall into locally optimal solutions, the tent chaotic map is employed to enhance the bat colony search ability for improving the randomness of bat algorithm, involves escaping from local extreme points and increasing the diversity of the bat colony. Finally, we embed the temperature and humidity sensors into the hardware-in-the-loop simulation platform to construct the near-actual physical environment. The performance and convergence of the proposed method are verified using both a pure digital simulation platform and a built-in hardware-in-the-loop simulation platform. Compared with basic bat algorithm (BA), particle swarm optimization algorithm (PSO) and chaotic bat algorithm (CBA), the proposed fully distributed chaotic bat algorithm (DCBA) have higher accuracy and can achieve the 98.41 % accuracy in fixed bias (FB) sensor faults, 96.96 % accuracy in complete failure (CF), 95.84 % in drift bias (DB) and 96.08 % accuracy in accuracy drops (AD).

The Touch programming language for swarm intelligent building application (APP) development effectively reduces the development difficulty and user programming threshold, making the building more intelligent. However, the features of Touch language such as intuitive modeling of building elements, parallel programming, and the implicit specification of internode communication lead to great challenges in the compilation process of Touch language to the low-level executable object code of swarm intelligent buildings, and the APP development efficiency is not high. This paper proposes a code conversion method from Touch to C language and its supporting tools, designs code conversion algorithms for Touch language elements used to describe distributed building physical objects and parallel computing mode, which supports the automatic conversion of high-level Touch language, which is user-oriented and shielded from the details of the underlying interactions, into the C language code for underlying execution, thus realizing an integrated process from high-level APP development to low-level hardware platform execution and improving the APP development efficiency.

Building Information Physical Model (BIPM) is a new type of special information model that integrates static information, dynamic interaction mechanism and physical mechanism information. However, BIPM lacks a data model with a statute description and structured storage of computable entities, which will not guarantee the interoperability of BIPM. Therefore, this study proposes a method of statutorily describing BIPM entities based on the ontology technology proposed to establish a unified description model for BIPM. Subsequently, the application of BIPM data model in the intelligent control of chiller is taken as an example to illustrate that BIPM data model supports open access on the computer.

Building digital twin (BDT) realizes real-time monitoring, prediction, and optimization control of the building system through the synchronization between the real world and the virtual platform, and improves the efficiency of building operation and maintenance. However, the changes in physical laws caused by the decline and aging of buildings make it difficult for the BDT models to depict the dynamic evolution mechanism of buildings and improve decision-making, which brings great challenges to the prediction and maintenance of buildings. To this end, an evolutionary method of digital twin model for building physics mechanisms is proposed, which integrates the internet of things (IoT), building information physical model (BIPM), and machine learning algorithms to build a self-evolution framework of digital twins for building physics mechanism, and supports high-precision modeling of BDTs. The advanced prediction (AP) model and autonomous decision-making (ADM) model for building physics mechanisms with self-evolution capability are designed, which support the autonomous correction of model parameters and the dynamic updating of the model driven by real-time data, and the ability to learn optimal control actions through interactive trial and error with the environment. The experimental results based on the settlement prediction and control case of underground engineering show that this evolutionary method can dynamically simulate the future evolution trend of the settlement law of underground engineering, and adjust the physical parameters to the ideal range to guide the evolution of underground engineering in a better direction. Compared with the existing methods, it has better prediction accuracy, interpretability, and generalization performance.

Download This Paper Open PDF in Browser Add Paper to My Library Share: Permalink Using these links will ensure access to this page indefinitely Copy URL Copy DOI

Image contour-based feature extraction method has been applied to some fields of image recognition and virtual reality. However, image contour features are easily susceptible to factors like noise, rotation and thresholds during extraction and processing. To solve the above problem, this paper proposes a contour coding image recognition algorithm based on level set and BP neural network models. Firstly, level set model is employed to extract the contours of images. Secondly, image coding method proposed herein is used to code images horizontally, vertically and obliquely. At last, BP neural network model is trained to recognize the image codes. Validity of the proposed algorithm is verified by using a set of actual engineering part images as well as MPEG and PLANE databases. The results show that the proposed method achieves high recognition rate and requires small samples, which also exhibits good robustness to external disturbances such as noise and image scaling and rotation.

People have high demands for comfort and technology in indoor environments. Gestures, as a natural and friendly human computer interaction (HCI) method, have received widespread attention and have been the subject of many research studies. Traditional approaches are based on wearable devices and cameras, which can be cumbersome to operate and infringe upon users’ privacy. Millimeter-wave (mmWave) radar avoids these problems by detecting gestures in a noninvasive manner. However, it encounters practical challenges in complex indoor environments, such as dynamic disturbance from surroundings, variable usage conditions and diverse gesture patterns, which conventionally require considerable manual effort to address. In this paper, we attempt to minimize human supervision and propose a noninvasive gesture recognition method named RaGe that involves a commercial mmWave indoor radar. First, a parameter optimization framework considering gesture prior constraints is proposed for radar configuration, which functions to weaken the disturbance from surroundings. Second, we alleviate data shortages in variable usage conditions and achieve low-cost data augmentation by applying affine transformations. Third, we combine deformable convolution operations with an unsupervised attention mechanism, thus exploring the intrinsic features involved in diverse gesture patterns. Experimental results show that RaGe is able to recognize 7 gestures with 99.3% accuracy and less human supervision, surpassing the state-of-the-art methods in comparative experiments.

Low-frequency vibrations, such as ocean waves, are widely distributed in nature and serve as a promising renewable energy source. Triboelectric nanogenerators (TENGs) have been shown to be an effective method for harvesting low-frequency vibration energy. However, most TENGs can only effectively harvest vibration energy in a single direction and a specific vibration mode. To solve the problem, we developed a disc-shaped liquid-solid triboelectric nano -generator (DLS-TENG) that can harvest vibration energy omnidirectionally. Benefiting from the high flexibility of the fluid and the ultra -high surface utilization of the disc structure, the DLS-TENG has the highest volumetric charge density and load driving capability in harvesting omnidirectional vibrational energy. Driven by seesaw vibrations with a frequency of 0.5 Hz and an amplitude of 30(degrees), one DLS-TENG successfully lit up 544 LEDs simultaneously, with a transferred charge of 1263 nC. Considering the random, irregular, and variable characteristics of most ambient vibrations, our omnidirectional TENG is more practical. The proposed DLS-TENG can achieve long-term and efficient natural vibration energy harvesting to power an increasing number of microsensors widely distributed in the field.

Building Information Physical Model (BIPM) is a new special information model in which information processes and physical processes are coupled and intertwined, integrating static information, dynamic interaction mechanisms and physical mechanisms, while how to model and verify the theory of BIPM becomes an urgent problem to be solved. In this paper, firstly, we further improve the BIPM conceptual framework to make the interaction between the information model, the physical model, the interaction model and the three sub-models more clear and complete. In this way, we achieve the purpose of integrating dynamic and static attribute information and physical information of buildings into one environment. Secondly, we combine the implementation logic of BIPM with a strict mathematical description to establish the theoretical model of BIPM, so that BIPM accurately and realistically reflects the behavioral state in physical space, realizes the two-way interaction of virtual physics, achieving the purpose of controlling physics with virtual and optimal regulation. Again, we validated the theoretical model of BIPM by formal modelling using Communication Sequential Process (CSP), which proved the reliability and correctness of BIPM. Further, we have built a BIPM prototype system in conjunction with a chiller to validate the proposed modelling approach, which proves the feasibility and effectiveness of the modelling approach. BIPM is expected to form a new paradigm for information model of the building, which will provide basic support for the development of new platforms such as BIPM-based building operation and maintenance and urban digital twin.

Currently, building energy consumption accounts for a considerable proportion of the world's energy consumption, e.g., 35 % in China, which has become a key concern with its rising proportion. Accurate prediction of building hourly energy consumption is key to realizing green, low-carbon, and energy-saving modern buildings. However, most of the current prediction methods are only based on dynamic data from IoT (Internet of Things) systems that may contain a large number of outliers, resulting in lower accuracy and reliability. To solve this problem, with the help of rich data provided by BIM (Building Information Modelling), we propose an approach named dynamic and static hybrid data analysis (D&S-HDA) that can provide a solution with better prediction accuracy. Technically, the novelties of D&S-HDA are fourfold. Firstly, we establish the D&S-HDA framework to obtain more accurate prediction outcomes, where the electricity consumption prediction results based on dynamic data analysis are weighted with the estimation values based on static data analysis. Secondly, in the dimension of dynamic data analysis, we design an improved temporal convolutional networks (TCNs) for parallelly outputting dynamic data samples to make the prediction results more intuitive. Thirdly, in the dimension of static data analysis, a novel concept of building hourly power consumption coefficient(BHPCC) is proposed, and its calculation method using static data analysis is designed to estimate hourly electricity consumption. Finally, in order to validate the effectiveness of our D&S-HDA approach, we design multidimensional evaluation metrics and conduct multi-group comparative experiments under different conditions, including climate models, electricity usage behaviour and time scales. The experimental results reveal that the proposed D&S-HDA approach outperforms current mainstream works in terms of root mean square error (RMSE), mean absolute error (MAE) and mean absolute percentage error (MAPE), with values of 1.5248, 1.0693 and 2.9505, respectively, which shows the efficiency and feasibility of the proposed D&S-HDA.

Electric field sensing has a wide range of applications, but conventional MEMS-based electric field sensors (MEMS-EFSs) exhibit poor resistance to vibration and measurement distortion due to their internal movable structures and electronic components that interfere with the electric field. To address these issues, we present a novel multilayer surface acoustic wave (SAW) EFS (SAW-EFS) for wireless quasi-static electric field detection. The SAW-EFS is composed of an aluminum (Al) interdigital transducer (IDT) and grating reflector deposited on a lithium niobate (LiNbO3) substrate with a silicon dioxide (SiO2) insulation layer. An Al film deposited on the SiO2 insulation layer also acts as an electric field guide layer to increase sensitivity. When an external quasi-static electric field is applied to the SAW-EFS, internal stress disturbs the SAW generated in the LiNbO3 substrate. This disturbance modifies the phase response of a signal transmitted back to a wireless reader from the SAW-EFS and allows for measurement of the external quasi-static electric field. We designed, fabricated, and tested the novel SAW-EFS and achieved a sensitivity of 0.74 degrees/kV/m with a nonlinear error of 1.24%.

Information is the core element to drive human-cyber-physical collaborations and promote the orderly operation of building activities in the entire lifecycle of buildings. More realistic and efficient description and sharing of building information has always been an important theme pursued in the field of architecture. To meet the rapidly growing demand for interactive collaboration between virtual and real building conditions, this study proposes a novel form of information description for buildings, namely a building information and physical model (BIPM), for realizing the true mapping and collaboration from building physical entities to the information space. The BIPM is composed of a building basic information model, a physical model, and an interaction model, and unifies the description of the external geometric attribute information and the internal physical mechanisms of buildings. The theoretical foundation and key technical system of the BIPM are discussed, and the application effectiveness and benefits of the BIPM are demonstrated using building chillers as an example. Furthermore, the application ecologies and values of the BIPM are analyzed. Research suggestions are proposed as follows: (1) deepening the research on BIPM theories and key technologies, (2) formulating serialized BIPM standards and specifications, and (3) developing BIPM building industry software tools to expand the BIPM application ecosystem. This study is expected to provide support for the development of new basic software for the building industry, involving architectural design, construction, operation and maintenance, and urban digital twins.

The remaining useful life (RUL) degradation under driving conditions is complex. The features from incremental capacity-differential voltage curves and electrochemical impedance spectroscopy (EIS) can be implemented to identify the battery degradation modes and predict RUL. This article proposes a light gradient boosting machine (LightGBM)-based framework with electrochemical theory to achieve RUL prediction under driving conditions. The degradation modes are identified as loss of conductivity, loss of active material, and loss of lithium ion, and the EIS is refined as ohmic resistance, charge transfer resistance, solid electrolyte interphase film resistance, and Warburg resistance. The LightGBM model is improved by the adaptive robust loss function to achieve multiloss functions adaptive adjustment for different cases and limit the effect of measurement noise on gradients. Based on the perspective of multitask learning, the Pearson correlation is analyzed to design the sharing principle, which ensures full use of features and reduce experimental costs. The proposed framework is validated by the database under four vibration cases (static, X -axis, Y -axis, and Z -axis). Experimental results demonstrate that the proposed framework is capable of providing accurate and steady RUL prediction under driving conditions even with measurement noise. The proposed framework could guide periodic maintenance and stable operation to avoid risks.

传统微电网能源管理策略中,电源侧被动跟随用电变化,负荷侧呈现刚性.柔性负荷能够通过改变自身用电行为调整负荷曲线,是发电调度的补充.通过介绍微电网调度策略发展前景引出源荷互动概念,根据调度模式和响应特性对柔性负荷进行分类,阐述了"源荷互动"在微电网日前和日内调度策略中的实现方式,重点介绍其调度模型的构建与求解,并与传统微电网调度策略进行比较.

Fully distributed intelligent building systems can be used to effectively reduce the complexity of building automation systems and improve the efficiency of the operation and maintenance management because of its self-organization, flexibility, and robustness. However, the parallel computing mode, dynamic network topology, and complex node interaction logic make application development complex, time-consuming, and challenging. To address the development difficulties of fully distributed intelligent building system applications, this paper proposes a user-friendly programming language called SwarmL. Concretely, SwarmL (1) establishes a language model, an overall framework, and an abstract syntax that intuitively describes the static physical objects and dynamic execution mechanisms of a fully distributed intelligent building system, (2) proposes a physical field-oriented variable that adapts the programming model to the distributed architectures by employing a serial programming style in accordance with human thinking to program parallel applications of fully distributed intelligent building systems for reducing programming difficulty, (3) designs a computational scope-based communication mechanism that separates the computational logic from the node interaction logic, thus adapting to dynamically changing network topologies and supporting the generalized development of the fully distributed intelligent building system applications, and (4) implements an integrated development tool that supports program editing and object code generation. To validate SwarmL, an example application of a real scenario and a subject-based experiment are explored. The results demonstrate that SwarmL can effectively reduce the programming difficulty and improve the development efficiency of fully distributed intelligent building system applications. SwarmL enables building users to quickly understand and master the development methods of application tasks in fully distributed intelligent building systems, and supports the intuitive description and generalized, efficient development of application tasks. The created SwarmL support tool supports the downloading and deployment of applications for fully distributed intelligent building systems, which can improve the efficiency of building control management and promote the application and popularization of new intelligent building systems.

Durability problems caused by friction loss have restricted the development of a solid-solid triboelectric nano -generator, which has provided an opportunity for the solid-liquid triboelectric nanogenerator. Ferrofluid has been used in the solid-liquid triboelectric nanogenerators due to its liquid and magnetization properties. In this study, we propose a solid-ferrofluid triboelectric nanogenerator (SF-TENG) for ultra-low-frequency vibration energy harvesting. This SF-TENG can harvest swing vibrations using friction electrification between the poly-tetrafluoroethylene shell and ferrofluid. To increase the moving speeds of charges, we applied a magnetic field to the SF-TENG to raise the flow velocity of the ferrofluid. The volume of ferrofluid and the magnetic field intensity applied were optimized to enhance the performance of the SF-TENG. We then characterized the SF-TENG by applying frequency swing vibrations of 0.1-0.5 Hz. When the frequency of the input swing was 0.5 Hz, the peak -to-peak value of the open-circuit voltages was 0.98 V, and the maximum instantaneous current was 1.05 nA. In addition, the output power was approximately 1.03 nW, and the power density was 0.0426 mW/m3. The peak output power of the SF-TENG parallel array reached 18.2 nW at the 700 M ohm load resistance. And the capacitor with capacity of 1 mu F can be charged to 1.5 V in 150 s.

The Heating, Ventilation and Air Conditioning (HVAC) system is a key system in buildings for providing energysaving and occupant-centered indoor services. Sensor fault diagnosis (SFD) is essentially important for HVAC systems since incorrect sensory measurements may destabilize system operations. Most SFD methods for HVAC systems require comprehensive manual knowledge or massive labeled data which is hardly available in diverse buildings. To reduce labor cost, transfer learning method is adopted in diagnosing HVAC sensor faults, however, it still encounters critical challenges, such as imbalanced data distribution and insignificant fault features. In this paper, an attention-empowered transfer learning method is innovatively proposed to enhance the capability of SFD in HVAC systems. Firstly, we introduce the multi attention-based module to characterize sensor faults in spatio-temporal domain. Secondly, we explore the relationship between source domain and target domain, and establish the model that enables useful knowledge mapping. Thirdly, to alleviate the effect of data discrepancy existed in new domains, a joint domain loss function is designed to enhance the domain adaptive ability. Experimental validation is carried out on three datasets from completely different real-world scenarios. Compared with existing methods (i.e., TCA, JAN and DDC), the proposed method achieves the highest average accuracy of 93 % in cross-domain building environments. The ablation studies also demonstrate the effectiveness of our method under diverse parameter settings, such as attention modules, fault types and data volume.