This is, what we aim to at our own factories. Read my introduction to a series of blogposts how we do this. Harnessing the power of artificial intelligence (AI), engineers at our manufacturing plant in Amberg can predict when a key component is likely to fail – up to 36 hours before the failure actually happens. This allows them to react in plenty of time to avoid a costly breakdown of the machine. In our electronics manufacturing facility in Amberg, we have several PCB cutting machines that are deployed for a number of our SIMATIC products – including the S7-300 and ET 200.
OSAKA--Summer spells fun for many, but not for air conditioner repair workers, who face incessant calls during the peak service period and often have to make repeated visits to fix a single problem. And since the average air conditioner has 2,000 or so components embedded inside, it's no easy task to figure out which parts they need to take with them when heading out on a repair call. To simplify life for those sweating to keep customers cool, leading air conditioner manufacturer Daikin Industries Ltd., based here, is relying on an artificial intelligence (AI) system to pick the parts. Few other firms in Japan are utilizing an AI system on such a large scale for repairs, Daikin officials said. As summer nears, the company's call center in Osaka's Chuo Ward begins being bombarded with calls from households and businesses requesting repairs.
Appliances, even large ones, are getting in on the action. But that doesn't mean you need to toss your old "dumb" stuff and buy brand new smart devices. Air conditioners are certainly one type of appliance that is heading down the smart path, but if you have a window or wall unit you already love (or can't afford to replace), you might consider turning your dumb unit into a smart A/C. With a few tweaks, you can convert the unit you have into a cooling solution you can turn on and off remotely with an app or through your favorite smart home ecosystems, such as Google Assistant or Alexa. A window or wall unit (or a portable A/C) works just fine when you manually turn it on with buttons, so why is it even necessary to make it smart?
EcoFactor is one of several startups with a cloud computing platform to manage and analyze data from smart thermostats and other home energy devices. But it also specializes in using that data to monitor and predict performance problems and impending failures of the air conditioners keeping houses cool. That kind of technology could have a lot of value to the companies that make heating, air conditioning and ventilation equipment -- enough to make it worth owning. On Tuesday, HVAC giant Trane announced it has acquired EcoFactor's energy analytics software for an undisclosed sum. Trane, a brand of Ingersoll Rand, plans to integrate EcoFactor's "unique artificial intelligence (AI) capabilities for energy efficiency and HVAC fault detection" into its existing Nexia home automation line.
Robots are increasingly picking up the slack in package distribution centers. Honeywell and Siemens have unveiled new machines that are capable of autonomously ferrying packages from the tractor trailer to the fulfillment center with surprising accuracy, according to Bloomberg. It comes as consumers increasingly expect two-day or even same-day delivery, causing shipping companies to embrace automation as a solution to meet the spike in demand. Both Honeywell and Siemens' robot unloaders drive up to the back of a tractor trailer and use machine learning to identify packages. And, the companies say their machines work just as fast, if not faster, than human employees.
The large thermal capacity of buildings enables heating, ventilating, and air-conditioning (HVAC) systems to be exploited as demand response (DR) resources. Optimal DR of HVAC units is challenging, particularly for multi-zone buildings, because this requires detailed physics-based models of zonal temperature variations for HVAC system operation and building thermal conditions. This paper proposes a new strategy for optimal DR of an HVAC system in a multi-zone building, based on supervised learning (SL). Artificial neural networks (ANNs) are trained with data obtained under normal building operating conditions. The ANNs are replicated using piecewise linear equations, which are explicitly integrated into an optimal scheduling problem for price-based DR. The optimization problem is solved for various electricity prices and building thermal conditions. The solutions are further used to train a deep neural network (DNN) to directly determine the optimal DR schedule, referred to here as supervised-learning-aided meta-prediction (SLAMP). Case studies are performed using three different methods: explicit ANN replication (EAR), SLAMP, and physics-based modeling. The case study results verify the effectiveness of the proposed SL-based strategy, in terms of both practical applicability and computational time, while also ensuring the thermal comfort of occupants and cost-effective operation of the HVAC system.
In many real-world planning problems with factored, mixed discrete and continuous state and action spaces such as Reservoir Control, Heating Ventilation and Air Conditioning (HVAC), and Navigation domains, it is difficult to obtain a model of the complex nonlinear dynamics that govern state evolution. However, the ubiquity of modern sensors allows us to collect large quantities of data from each of these complex systems and build accurate, nonlinear deep neural network models of their state transitions. But there remains one major problem for the task of control - how can we plan with deep network learned transition models without resorting to Monte Carlo Tree Search and other black-box transition model techniques that ignore model structure and do not easily extend to mixed discrete and continuous domains? In this paper, we introduce two types of nonlinear planning methods that can leverage deep neural network learned transition models: Hybrid Deep MILP Planner (HD-MILP-Plan) and Tensorflow Planner (TF-Plan). In HD-MILP-Plan, we make the critical observation that the Rectified Linear Unit (ReLU) transfer function for deep networks not only allows faster convergence of model learning, but also permits a direct compilation of the deep network transition model to a Mixed-Integer Linear Program (MILP) encoding. Further, we identify deep network specific optimizations for HD-MILP-Plan that improve performance over a base encoding and show that we can plan optimally with respect to the learned deep networks. In TF-Plan, we take advantage of the efficiency of auto-differentiation tools and GPU-based computation where we encode a subclass of purely continuous planning problems as Recurrent Neural Networks and directly optimize the actions through backpropagation. We compare both planners and show that TF-Plan is able to approximate the optimal plans found by HD-MILP-Plan in less computation time. Hence this article offers two novel planners for learned deep neural net transition models: one optimal method for mixed discrete and continuous state and actions (HD-MILP-Plan) and a scalable alternative for large-scale purely continuous state and action problems (TF-Plan).
In industrial systems, certain process variables that need to be monitored for detecting faults are often difficult or impossible to measure. Soft sensor techniques are widely used to estimate such difficult-to-measure process variables from easy-to-measure ones. Soft sensor modeling requires training datasets including the information of various states such as operation modes, but the fault dataset with the target variable is insufficient as the training dataset. This paper describes a semi-supervised approach to soft sensor modeling to incorporate an incomplete dataset without the target variable in the training dataset. To incorporate the incomplete dataset, we consider the properties of processes at transition points between operation modes in the system. The regression coefficients of the operation modes are estimated under constraint conditions obtained from the information on the mode transitions. In a case study, this constrained soft sensor modeling was used to predict refrigerant leaks in air-conditioning systems with heating and cooling operation modes. The results show that this modeling method is promising for soft sensors in a system with multiple operation modes.
Early fault detection using instrumented sensor data is one of the promising application areas of machine learning in industrial facilities. However, it is difficult to improve the generalization performance of the trained fault-detection model because of the complex system configuration in the target diagnostic system and insufficient fault data. It is not trivial to apply the trained model to other systems. Here we propose a fault diagnosis method for refrigerant leak detection considering the physical modeling and control mechanism of an air-conditioning system. We derive a useful scaling law related to refrigerant leak. If the control mechanism is the same, the model can be applied to other air-conditioning systems irrespective of the system configuration. Small-scale off-line fault test data obtained in a laboratory are applied to estimate the scaling exponent. We evaluate the proposed scaling law by using real-world data. Based on a statistical hypothesis test of the interaction between two groups, we show that the scaling exponents of different air-conditioning systems are equivalent. In addition, we estimated the time series of the degree of leakage of real process data based on the scaling law and confirmed that the proposed method is promising for early leak detection through comparison with assessment by experts.
Heating, Ventilation, and Air Conditioning (HVAC) is extremely energy-consuming, accounting for 40% of total building energy consumption. Therefore, it is crucial to design some energy-efficient building thermal control policies which can reduce the energy consumption of HVAC while maintaining the comfort of the occupants. However, implementing such a policy is challenging, because it involves various influencing factors in a building environment, which are usually hard to model and may be different from case to case. To address this challenge, we propose a deep reinforcement learning based framework for energy optimization and thermal comfort control in smart buildings. We formulate the building thermal control as a cost-minimization problem which jointly considers the energy consumption of HVAC and the thermal comfort of the occupants. To solve the problem, we first adopt a deep neural network based approach for predicting the occupants' thermal comfort, and then adopt Deep Deterministic Policy Gradients (DDPG) for learning the thermal control policy. To evaluate the performance, we implement a building thermal control simulation system and evaluate the performance under various settings. The experiment results show that our method can improve the thermal comfort prediction accuracy, and reduce the energy consumption of HVAC while improving the occupants' thermal comfort.