WO2018004464A1 - Modélisation, optimisation et diagnostic d'installations de refroidissement reposant sur un apprentissage machine à grande échelle - Google Patents

Modélisation, optimisation et diagnostic d'installations de refroidissement reposant sur un apprentissage machine à grande échelle Download PDF

Info

Publication number
WO2018004464A1
WO2018004464A1 PCT/SG2017/050324 SG2017050324W WO2018004464A1 WO 2018004464 A1 WO2018004464 A1 WO 2018004464A1 SG 2017050324 W SG2017050324 W SG 2017050324W WO 2018004464 A1 WO2018004464 A1 WO 2018004464A1
Authority
WO
WIPO (PCT)
Prior art keywords
chiller
equipment
predict
data
speed
Prior art date
Application number
PCT/SG2017/050324
Other languages
English (en)
Inventor
Kok Soon Chai
Choon Hoo LAI
Original Assignee
Kirkham Group Pte Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Kirkham Group Pte Ltd filed Critical Kirkham Group Pte Ltd
Priority to SG11201810279QA priority Critical patent/SG11201810279QA/en
Publication of WO2018004464A1 publication Critical patent/WO2018004464A1/fr

Links

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators

Definitions

  • Embodiments of the invention relate to energy or management system (EMS/BMS) for buildings and chiller plants, particularly to a data driven, or a hybrid rule-based and data driven EMS/BMS, and method and system for modeling, optimizing and evaluating chiller plant and chiller plant equipment.
  • EMS/BMS energy or management system
  • Chiller plant optimization is one of the most crucial tasks to smart building systems, as the energy consumption of a chiller plant comprises over 40% of the total energy consumption of a modern building. Poor efficiency is commonly observed in existing chiller plant systems, due to the excessive overhead and technical challenges faced in manual tuning. In practice, a large number of chiller plants and buildings are optimized during the first few months in operation, when experienced engineers spend huge efforts on fine-tuning the chiller plants to achieve near-optimal performance. However, the efficiency of these chiller plants deteriorates quickly when the engineers with expertise leave the projects, such that the configuration of the chiller plant does not adapt well to the varying environmental and equipment conditions. A fully optimized chiller plant may run at excellent efficiency during office hours, but performs poorly at nights/weekends/public holidays.
  • Chiller plant power is calculated by the summation of the total power consumption of chiller, chilled and condenser water pumps and cooling towers. Sophisticated tradeoff of comfort and equipment operating conditions etc. are required to minimize the total power consumption of the chiller plant over a long period of time.
  • the existing method relies on a data driven model that accurately models and optimizes a type of chiller plant for a short period of time. This method requires time consuming effort to develop new models for different types of chiller
  • the model is also a best fit for the data for a relatively short period of time, but it loses predicting accuracy over new data set after a period of chiller plant operation.
  • the invention can be implemented, but not limited to as an energy or management system (EMS/BMS) for buildings and chiller plants.
  • the invention is to transform existing EMS/BMS from rule-based to a data driven, or a hybrid rule-based and data driven EMS/BMS.
  • control engineers develop a set of rules based on domain expertise in advance during the design stage.
  • the rule-based EMS/BMS use predetermined rules to control HVAC equipment with set points.
  • the field engineers and technicians update the set points to improve energy efficiency, comfort or maintenance.
  • the rule-based EMS/BMS lacks the ability to improve by itself with experience because it lacks the ability to learn from the data.
  • the invention provides the EMS/BMS with ability for autonomous learning and control.
  • the invention is related to the application of a data driven, machine learning-based control system (may be referred to as "Learning-based Energy Optimization system” or “LEO system”) that uses machine learning model for diagnostics and energy efficiency optimization of chiller plants.
  • the system reads and processes measurement and verification (M&V) sensor data for chiller plant such as chilled water and condenser temperatures and flow rates, equipment power, and learns to represent the equipment in the chiller plants to predict equipment and chiller plant power.
  • M&V measurement and verification
  • One aspect of the invention covers the application of a method and system to use data driven model and sub-models, e.g. neural networks with inputs layers, multiple hidden layers, and output layers, to represent the actual equipment and predict equipment and chiller plant power, performance and efficiency.
  • the system learns to represent the chiller plant and equipment high level characteristics from relative accuracy of the predicted values. It further learns to represent detailed equipment characteristics such as but not limited to equipment efficiency, performance etc. to provide data driven, detailed and actionable diagnostics information for further analysis, diagnostics or energy efficiency optimization.
  • Another aspect of the invention covers the application of the data driven and deep learning with model and sub-models to predict and evaluate efficiency and performance of the system and various equipment.
  • the model and sub-models are trained to predict system and equipment power and performance using trained data, X train , and evaluated with a set of accuracy matrix, M acc .
  • the model and sub-models are evaluated with a set of cross validation data, X cr0S s, for accuracy evaluation.
  • M acc accuracy matrix
  • the model and sub-models are used as the baseline for predicting power, performance and efficiency from the M&V data, X tes t, of the equipment and of chiller plant in the future.
  • the model and sub-models predict the performance values of the system and equipment to be used for comparison for the actual performance values.
  • the system refers to the accuracy matrix and variance in performance of system and subsystems between the training X train , cross validation X cross and testing x te s t data sets to conclude performance evaluation of the system and subsystem over time.
  • Another aspect of the invention covers a method and system that refers to the performance matrix of equipment for large scale chiller plant comparisons and cross learning.
  • Another aspect of the invention covers a data driven "universal" model that generalizes the system and equipment performance, power and efficiency using the measurement and verification sensor data of the chiller plants that the model is trained on, as well as the cross validation data and testing data that the model have not been trained on. This includes a method and system to achieve the best trade-off for optimizing the generalization of any chiller plants. It includes a method to model the chiller plant life cycle for continuous and automated learning, modelling and optimization.
  • a computer-implemented method comprises: training a plurality of prediction models using first baseline data, the prediction models being for chiller plant and a plurality of equipment comprising cooling tower (CT), condenser water pump (CWP), chiller, chilled water pump (CHWP); computing, using the prediction models, a plurality of predicted parameters of the plurality of equipment and the chiller plant using test data; computing a plurality of differential parameters of the plurality of equipment based on the predicted parameters of the plurality of equipment and a plurality of actual parameters of the plurality of equipment; computing a differential parameter of the chiller plant based on the predicted parameter of the chiller plant and an actual parameter of the chiller plant;
  • CT cooling tower
  • CWP condenser water pump
  • CHWP chilled water pump
  • a differential parameter resulting from chiller plant optimization by subtracting the differential parameters of the plurality of equipment from the differential parameter of the chiller plant; ascertaining a presence of abnormality in the differential parameter resulting from chiller plant optimization; and if the presence of abnormality in the differential parameter resulting from chiller plant optimization is ascertained, generating a first notification which identifies a request for human intervention.
  • the computer-implemented method may further comprise: ascertaining a presence of abnormality in any one of the plurality of equipment based on the differential parameters of the plurality of equipment; and if the presence of abnormality in any one of the differential parameters of the plurality of equipment is ascertained, performing at least one of the following steps: generating a second notification which identifies the presence of abnormality in the any one of the plurality of equipment, and training one of the prediction models, which corresponds to the any one of the plurality of equipment, using second baseline data.
  • the parameters may be power, or a combination of power, flow and temperature, depending on the prediction parameters of the prediction models being used.
  • a system comprises at least one computing unit; and at least one memory storage for storing computer-executable instructions that, when executed by the at least one computing unit, cause performance of operations comprising any one of the computer-implemented methods described in the above paragraphs.
  • Figure 1 shows a system architecture of the LEO system
  • Figure 2A shows a machine learning life cycle that addresses the challenges of scalability, adaptability and learning
  • Figure 2B shows a basic concept of generalization of model for chiller plants, and four phases required to build a model that achieves universal fitting of chiller plant data;
  • Figure 3A shows a prediction model for chiller plant
  • Figure 3B shows prediction models for chiller plant equipment e.g. cooling tower, condenser water pump, chiller model, chilled water pump, using an equipment performance decomposition-based approach with increasing levels of abstraction;
  • chiller plant equipment e.g. cooling tower, condenser water pump, chiller model, chilled water pump, using an equipment performance decomposition-based approach with increasing levels of abstraction;
  • Figure 3C shows one embodiment of prediction models for chiller plant equipment, e.g. cooling tower, condenser water pump, chiller model, chilled water pump;
  • chiller plant equipment e.g. cooling tower, condenser water pump, chiller model, chilled water pump;
  • Figure 3D shows another embodiment of prediction models for chiller plant equipment, e.g. cooling tower, condenser water pump, chiller model, chilled water pump;
  • Figure 3E shows one example of a prediction model for cooling tower;
  • Figure 3F shows one example of a prediction model for condenser water pump
  • Figure 3G shows one example of a prediction model for chilled water pump
  • Figure 3H shows another embodiment of prediction models for chiller plant equipment, based on Figures 3C, 3E to 3G;
  • Figure 4 shows a prediction process using the equipment performance decomposition-based approach
  • Figure 5 shows that the LEO system provides visualization data with targeted areas for human intervention and automatic optimization as compared to existing HVAC Big Data Tools
  • Figure 6 shows that LEO system performs machine and statistics machine learning to deliver two types of results
  • Figure 7 shows an implementation of block 415 to compare predicted and actual value of condenser pump power to detect abnormality
  • Figure 8 shows introduction of high variances to training data for cooling tower by the invention
  • Figure 9 shows a comparison of predicted total chiller plant power, actual total chiller plant power and a deviation therebetween
  • Figure 10 shows evaluation of chiller performance in which baseline data is provided during baseline time period 1 to 17 April while test data is provided during test period 18 March to 23 May;
  • Figure 1 1 shows a representation of optimization options, e.g. CWP flow and CT approach, and the corresponding power requirement;
  • Figure 12 shows a schematic representation of a data driven, or a hybrid rule-based and data driven EMS/BMS.
  • Embodiments described in the context of one of the methods or devices or systems are analogously valid for the other methods or devices or systems. Similarly, embodiments described in the context of a method are analogously valid for a system or device, and vice versa.
  • each other denotes a reciprocal relation between two or more objects, depending on the number of objects involved.
  • Coupled and related terms are used in an operational sense and are not necessarily limited to a direct physical connection or coupling.
  • two devices may be coupled directly, or via one or more intermediary devices.
  • devices may be coupled in such a way that data or information may be passed therebetween without sharing physical connection with each other.
  • coupling exists in accordance with the aforementioned definition.
  • power includes references to “power consumption” and may be interchangeably used
  • model and “sub-model” include references to “prediction models” and “machine learning models”, and may be interchangeably used
  • cooling load includes references to “cooling tonnage” and may be interchangeably used.
  • the term “deviation”, depending on context, refers to absolute difference between values, or a difference between one of a set of values and some fixed value, usually the mean of the set, and therefore may be interchangeably used with the term “difference”.
  • Figure 1 shows the system architecture of LEO system that receives real time M&V (measurement and verification) data from chiller plant, or historical data from different sources to trigger continuous machine learning life cycles.
  • a machine learning life cycle includes preprocessing, optimization and post-processing.
  • Figure 2A shows the novel machine learning life cycle that addresses the challenges of scalability, adaptability and learning.
  • the machine learning life cycle is divided into two major phases, namely i) model training phase and ii) large scale machine learning-based prediction and optimization phase.
  • Model training phase (in blocks 201 a and 201 b of Figure 2A)
  • the machine learning phase involves the development of a "universal model" that generalizes by fitting accurately to the measurement and verification data of a smaller sample of chiller plants.
  • the model comprises of sub-models that represent performance, power and efficiency of equipment such as chillers, chilled water and condenser water pumps, cooling towers.
  • the equipment list can be extended to airside equipment such as air handling units and fan coil units etc.
  • the main objective in the training phase is to achieve the best fit for a relative small sample of chiller plants with the M&V data t-Phase, while satisfying the best fit for large scale of chiller plants' M&V data that the model is not trained to fit in the training phase.
  • the "universal model” is trained using the X t -phase data, but it is expected to predict performance, power, performance and efficiency of future M&V data X m i-Phase without reprogramming. Deep neural network and multi-level regression model would likely be the best way to build the universal model.
  • Ref [3] Wei describes a data driven method to model a chiller plant. Wei applies BFGS (broydene- fletcheregoldssenshanno) method to a one-output-unit MLP (multi-layer perceptron) to train a network to represent the prediction model. Monfet and Lee also applied neural network to represent prediction models that predict single output. These models are black box approaches that predict an output, e.g. chiller plant power or efficiency with multiple inputs. The invention applies a novel deep learning approach that decomposes a chiller plant model to multiple sub-models e.g. equipment models (see Figure 3B), to form a final prediction model.
  • the LEO system with "universal model” is ready for large scale machine learning in this phase. All the tasks performed in the large scale machine learning phase are automated, and LEO system will only prompt for user intervention if it detects abnormal sensor data that is beyond uncertainty levels.
  • the large scale learning phase is divided into 5 tasks: a) Automatic model training and fine tuning for a specific chiller plant (in block 202).
  • the LEO receives sensor data from different M&V data sources, X m
  • Figure 2B shows the novel framework that LEO system applies for the development of the prediction model for the chiller plant. It further applies the novel equipment decomposition-based model development approach to improve the speed and accuracy of model training.
  • b) Optimization in block 203. It shall trigger an optimization program to determine the optimum values of certain set points, SP m i- Ph ase that minimize total chiller plant power consumption. Block 203 may be performed using existing methods.
  • LEO system will apply the differential equipment performance approach to develop a story with time line and descriptions on the changes of equipment and chiller plant performance and energy efficiency. LEO recursively splits the raw data into different time periods based on the differential equipment performance approach.
  • the invention applies the concept of differential equipment performance to evaluate i) the effectiveness of energy efficiency optimization algorithm, ii) the deviation of equipment performance and efficiency and decide how to retrain the universal model to improve fitness to the M&V data, and manage uncertainty.
  • the task is started once the model's fitness to the M&V data is in question.
  • the localized machine learning is a localized, sub-model training approach that trains for fitness of the data to individual equipment,
  • Stop training 208 The task is started once the uncertainty of the data accuracy exceeds certain level, and the sensor data is not fit for input to the model for optimization. A user is informed to fix the sensor data before machine learning can resume optimization.
  • the major novelties are equipment decomposition-based model development approach in block 202, differential equipment performance approach in block 204, and methods to evaluate the effectiveness of optimization algorithm and deviation of equipment performance in block 205.
  • Universal model is a multi-model based on a hybrid of deep neural network supported by continuous machine learning life cycles. The novelty is in model development process as well as the continuous machine learning life cycles.
  • Figure 2B shows that 4 phases are required to build a model that achieves universal fitting of chiller plant data.
  • Chiller plant M&V data can be modeled as inputs x .. x n to be associated with one or more outputs y (see Figure 3A).
  • the model would learn a set of weights w ⁇ . -wTM and compute their outputs f(x,w).
  • the first requirement is an optimization problem to minimize total chiller plant power vs total chiller plant cooling tonnage, i.e.
  • Figures 3A and 3B show a novel equipment performance chwp chiller cwp ct air
  • the third requirement is a Phase 3 requirement that would be met by modeling special features that detect changes in the life cycle of a chiller plant.
  • Figure 3A and 3B show a model and sub-models for learning to represent chiller plants with a similar architecture with different level of abstractions.
  • the sub-models total chwp chiller cwp ct air
  • the f(x) C hw P for block 309 in Figure 3B represents the power and efficiency for chilled water pumps with data sets of flow rates and other features as inputs for training.
  • the f(x) cwp block 307 in figure 3B also represents the power and efficiency for condenser pumps using features such as flow rates as inputs.
  • the f(x) ct and f(x) C hiiier that represent the power and efficiency of cooling towers and chillers are significantly more difficult to be modelled.
  • the motivation of the algorithm is to learn to model the power and efficiency of the cooling towers and chillers to trade off better ratios of total power over total cooling tonnage.
  • chiller power consumption f(x) C hiiier for block 308 in figure 3B can be modelled by independent parameters stated in the chiller manufacturing datasheet such as chilled water supply set point, condenser supply temperature, usgpm/rt (flow rate) for chilled water and condenser water, and the cooling tonnage supplied by the chiller.
  • the problem is constructed such that given some noisy observations of a dependent variable at certain values of the independent variables ⁇ wet bulb, dry bulb, rh, cooling load and may other variables ⁇ , what is the best estimate of the dependent variable at a new value, f(x) ct for block 306 in figure 3B.
  • the chiller plant power consumption f(x)chiiierpiam is modelled by independent variables such as weather (such as wet bulb, relative humidity (RH) and dry bulb), cooling load, and as in Figure 3A.
  • the novel LEO modelling is based on a divide and conquer-approach that decomposes a chiller plant power prediction problem to sub-models for better efficiency and useful statistical inference.
  • the following is the original mathematical problem.
  • P lola i refers to total equipment power
  • P chwp refers to chilled water pump power
  • P chi n er refers to chiller power
  • P cwp condenser water pump power
  • P c refers to cooling tower power
  • P air refers to air side equipment power.
  • R total refers to total cooling load.
  • E total refers to equipment efficiency
  • E chwp refers to chilled water pump efficiency
  • E chi iier refers to chiller efficiency
  • E cwp refers to condenser water pump efficiency
  • E c refers to cooling tower efficiency
  • E air refers to air-side equipment efficiency.
  • the novelty of the decomposition approach is the architecture levels of abstractions with multiple layers for chiller plants.
  • the first motivation for the modelling with architecture level of abstractions is to learn to represent the chiller plants equipment powers, and ultimately infer equipment and chiller efficiency from the representation.
  • the second motivation is to construct the architecture levels of abstractions that will generalize to represent power for any chiller plant without reprogramming.
  • Figure 3A describes the basic representation system of a chiller plant from data.
  • Figure 3B shows a specific representation learning method for a chiller plant's sensor data that is based on increasing levels of abstraction. It starts with low level abstractions such as flow rates, temperatures and powers, and progresses to project features to power and performance of specific equipment types. The projected features to specific equipment types are used to train to predict powers of the equipment types.
  • Figure 3B describes geometrical connections between representation learning that receives measurement and verification (M&V) data of a chiller plant and transforms the M&V data into equipment related subset features.
  • M&V measurement and verification
  • Many existing feature engineering methods can be applied to transform full features to subset features but they do not describe the specific geometrical connections for chiller plants.
  • the advantages of the representation learning method described in figure 3B are the faster speed of training subset features (blocks 302- 305) to equipment specific output values (blocks 306-309), and the availability of the middle levels of abstraction for further equipment specific performance evaluation.
  • the training speed is particularly important for adaptive control systems, e.g. for HVAC or manufacturing, that make real time control and decision makings.
  • Features engineering, representation learning from data etc. may be based on existing methods, but the geometrical connections for the representation learning are novel.
  • a set of prediction models are provided for a chiller plant and a plurality of equipment comprising cooling tower, condenser water pump, chiller and chilled water pump. These models are configured to train or machine learn from baseline data and thereafter predict parameters, e.g. power, flow and/or temperature, for their respective chiller plant or equipment during test period.
  • Figure 3A shows a prediction model for chiller plant, e.g. chiller plant model 320, which is configured to predict chiller plant power based on weather and cooling load (RT). Weather and cooling load are independent variables.
  • chiller plant model 320 which is configured to predict chiller plant power based on weather and cooling load (RT).
  • RT weather and cooling load
  • FIG. 3C illustrates a prediction model for various chiller plant equipment (hereinafter may be referred to as "equipment").
  • a first prediction model 306 is configured to predict a condenser water temperature into chiller (cwshdr); a second prediction model 307 configured to predict a condenser water flow in/out chiller (cwfhdr); a third prediction model 309 is configured to predict a chilled water flow in/out chiller (chfhdr); and a fourth prediction model 308 is configured to predict a chiller power (chkw) based on the condenser water temperature into chiller (cwshdr), the condenser water flow in/out chiller (cwfhdr), the chilled water flow in/out chiller (chfhdr), a cooling load and a chiller set-point (chsp).
  • the first prediction model 306 includes a first and a second sub-model.
  • the first sub-model 306a e.g. cooling tower model (CT), which is for cooling tower equipment is configured to predict cooling tower power ("ctkw"), e.g. in kilowatts, based on VSD (variable speed drive) speed of cooling tower fan ("ct_speed”).
  • CT cooling tower model
  • CWTM condenser water temperature model
  • CWTM condenser water temperature model
  • the second prediction model 307 includes a third and a fourth submodel.
  • the third sub-model 307a e.g. condenser water flow model (CWFM), which is for condenser water pump equipment, is configured to predict condenser water flow in/out of chillers ("cwfhdr") based on VSD speed of condenser water pump ("cwp speed”).
  • the fourth sub-model 307b e.g. condenser water pump model (CWP), which is for condenser water pump equipment, is configured to predict condenser water pump power (“cwpkw”) based on VSD speed of condenser water pump (“cwp speed”).
  • the third prediction model 309 includes a fifth and a sixth sub-model.
  • the fifth sub-model 309a e.g. chilled water pump model (CHWP), which is for chilled water pump equipment, is configured to predict chilled water pump power ("chwpkw") based on VSD speed of chilled water pump (“chwp speed”).
  • the sixth sub-model 309b e.g. chilled water flow sub- model (CHFM), which is for chilled water pump equipment, is configured to predict chilled water flow in/out of chillers (“chfhdr”) based on VSD speed of chilled water pump (“chwp speed”).
  • CHWP chilled water pump model
  • CHFM chilled water flow sub- model
  • the fourth prediction model 308, e.g. chiller model 308, which is for chiller equipment, is configured to predict chiller power ("chkw”) based on condenser water flow in/out of chillers (“cwfhdr”), condenser water temperature into chillers (“cwshdr”), chilled water flow in/out of chillers (“chfhdr”), cooling load and chilled water set point (“chsp"). Cooling load and chilled water set point (“chsp”) are independent variables.
  • the set of prediction models may further comprise a fifth prediction model 310, e.g chiller plant equipment model (see Figure 3B), which is configured to predict total equipment power based on cooling tower power ("ctkw”), condenser water pump power (“cwpkw”), chiller power (“chkw”) and chilled water pump power (“chwpkw”) from prediction models 306, 307, 308, 309.
  • a fifth prediction model 310 e.g chiller plant equipment model (see Figure 3B), which is configured to predict total equipment power based on cooling tower power (“ctkw"), condenser water pump power (“cwpkw”), chiller power (“chkw”) and chilled water pump power (“chwpkw”) from prediction models 306, 307, 308, 309.
  • Figure 3E shows another example of the first prediction model of Figure 3C.
  • the first prediction model 306 of Figure 3E is configured to predict condenser water temperature into chiller (cwshdr) based on weather data, cooling load, cooling tower power
  • FIG. 3G shows another example of the third prediction model of Figure 3C.
  • the third prediction model 309 of Figure 3E is configured to predict chilled water flow in/out chiller (chfhdr) based on chilled water pump power (chwpkw).
  • any or all of the first, second, third prediction models of Figure 3D may be replaced by the respective model of Figures 3E, 3F and 3G, and the predicted parameters would be modified according to the replacement models as described in relation to Figures 3E, 3F and 3G.
  • Performance evaluation process for a chiller plant to meet phase 3's requirement in Figure 2B is explained below. Performance evaluation is based on the concept of comparing the actual present power (Pow present ) versus the actual historical power (Pow historica i) at similar conditions. The conditions are the reverse projection of the actual power consumption to the prediction features in blocks 306-309 in figure 3B. This can be achieved using a couple of methods, e.g. deep learning models that estimate the relationship between dependent variables (blocks 306-309), e.g. powers, and independent variables, or features (blocks 302-309), e.g. flow rates, temperatures and powers.
  • Equipment performance decomposition-based approach in Figure 3B builds a prediction model that estimates the equipment and plant level dependent variables, e.g. power consumption, using some given independent variables. a) Equipment evaluation.
  • a negative differential power can be used to infer a reduction in power consumption by equipment with similar independent variables in blocks 306-309 in figure 3B.
  • the performance evaluation can be done for different levels of abstraction as stated by block 31 1 in figure 3B.
  • the energy efficiency of equipment and chiller plant can be computed by dividing the summation of power over summation of cooling tonnage.
  • Figure 4 shows a prediction process which uses equipment performance decomposition-based approach. While Figure 4 shows the process being applied to equipment, the process may be applied to chiller plant in a similar manner.
  • an operator decides what the objective of the prediction process is.
  • objective 1 Continuous chiller plant representation learning and automatic optimization
  • objective 2 Story telling from the M&V data for diagnostics.
  • LEO divides raw or existing M&V data from sensors into different time periods, and classifies them as baseline data, cross-validation data and test data.
  • LEO classifies the M&V data into a baseline, a cross validation and a number of (or at least one) test periods.
  • baseline data data from baseline time period
  • cross-validation data data from cross-validation time period
  • test time period data from test time period
  • the cross-validation time period may be a subset of the baseline time period.
  • the baseline time period and the test time period may or may not be mutually exclusive.
  • prediction models for equipment 306a, 306b, 307a, 307b, 308, 309a, 309b are trained to predict equipment power using baseline data. Training may be performed by neural network model, Gaussian process, or other suitable methods, to produce trained prediction models, e.g. cooling tower model 306a to predict cooling tower power, condenser water pump model 306b, 307a, 307b to predict condenser water pump power, chilled water pump model 309a, 309b to predict chilled water pump power, chiller model 308 to predict chiller power (see blocks 407a, 407b, 407c, 407d).
  • prediction model 320 for chiller plant is trained using baseline data to produce a trained chiller plant model 320 to predict chiller plant power.
  • the trained prediction models after training in block 405, are used to predict power for each equipment and for the selected time periods of block 403.
  • a predicted power is computed for each equipment.
  • a predicted power is computed for each equipment.
  • test data a predicted power is computed for each equipment.
  • predicted power is computed for chiller plant separately, using baseline, cross-validation and test data.
  • Blocks 41 1 a, 41 1 b and 41 1 c analyze the uncertainties of the various data sets to evaluate the confidence levels of the sensor data for the prediction models.
  • the predicted power computed using baseline data may be compared with the predicted power computed using cross-validation data (see block 409b) to compute a deviation.
  • predicted power computed using baseline data is compared with predicted power computed using cross-validation data to compute a deviation therebetween. Similar comparison and/or computation of deviation is also performed for each of the remaining equipment i.e. chilled water pump, condenser water pump, chiller, as well as for chiller plant.
  • model accuracy or fitness e.g. in terms of resolving bias and overfitting, is analysed for each equipment based on the above-computed deviation between predicted power using baseline data and predicted power using cross-validation data. For example, for cooling tower, if the computed deviation falls within a predetermined threshold or limit, accuracy of the cooling tower model is validated. However, if the computed deviation exceeds the predetermined threshold or limit, the cooling tower model is not accurate or is unfit and may require re-training of the cooling tower model. If re-training of the cooling tower model is required, the process proceeds or returns to block 403 where a different baseline data is to be selected and training of the cooling tower model takes place based on the selected different baseline data.
  • a presence or absence of abnormality in equipment is ascertained based on a change in performance of each equipment.
  • Change in equipment performance is computed using differential approach of equations 5 and 6 and using predicted and actual power for test period. For example, for condenser water pump, a predicted power computed from test data is compared with actual power during test period to compute a differential power. Similar computation is performed to compute separate differential powers for the remaining equipment, e.g. chilled water pump, condenser water pump, chiller, as well as for chiller plant.
  • the computed differential power of an equipment as computed in block 415 is compared against a respective predetermined threshold. If the computed differential power exceeds the predetermined threshold, a notification is generated and provided to an operator to notify a presence of abnormality in the equipment and/or prompt the operator to perform manual check on the abnormal equipment. Further, the process may proceed or return to block 403 to re-train the particular abnormal equipment model based on a different baseline data. The foregoing comparison and/or notification steps are similarly performed for each equipment.
  • Figure 7 shows an implementation of block 415 to compare predicted and actual value of condenser pump power to detect abnormality in condenser pump.
  • formulas such as mean error square, or many other formulas to measure the errors can be applied.
  • a high deviation can be inferred as an increase in condenser power consumption for similar flow rates.
  • similar power is observed on 22 nd March and 28 th March, however, flow rate on 22 nd March is higher while flow rate on 28 th March is lower.
  • An increased deviation of around 24%, from baseline value, on 28 th March infers a presence of abnormality in the condenser water pump.
  • scatter diagram, or scatter plot the plot uses condenser flow rates to determine power consumption of the condenser pumps.
  • Figure 10 shows another implementation of block 415 to compare predicted and actual value of chiller power to detect abnormality in chiller.
  • baseline time period is from 1 to 17 April and baseline data is represented by line 1001 ; test period is from 18 March to 23 May and line 1002 represents a percentage deviation between predicted and actual power during the test period.
  • the percentage deviation may be computed by dividing an absolute difference between actual power and predicted power by actual power, and expressing the quotient in percentage.
  • Change in equipment efficiency may also be evaluated as efficiency may be derived from change in equipment performance, e.g. computed as a quotient of power or differential power over cooling tonnage.
  • the LEO system may perform recursive searches to identify the change in equipment performance (block 415) to infer the root causes for the change of chiller plant efficiency.
  • the recursive searches may be performed by splitting the raw data into multiple time periods, repeating the computations of block 415, and comparing equipment performance and/or efficiency over these multiple time periods.
  • Block 417 evaluates the effectiveness of chiller plant optimization.
  • a differential power or change in power consumption contributed by chiller plant optimization is computed.
  • the differential powers of total equipment and of chiller plant are computed.
  • total equipment differential powers the differential powers computed in block 415 for each equipment are added up or summed to compute or obtain a summation which is referred to as "total equipment differential powers".
  • a predicted power computed from test data, using the chiller plant model 320, is compared with actual power of chiller plant during test period to compute a difference therebetween.
  • a differential power resulting from chiller plant optimization is computed by subtracting the total equipment differential powers from the differential power of the chiller plant, and may be used to evaluate the effectiveness of chiller plant optimization.
  • the total change of equipment performance and/or efficiency may be used to isolate the results of optimum control strategies, and the change of sensor accuracies.
  • the computed differential power resulting from chiller plant optimization implies an improvement in chiller plant operation, e.g. the computed differential power resulting from chiller plant optimization is a negative value or becomes an increasingly negative value over a period of time, this shows that power consumption has decreased, chiller plant optimization has been effective and therefore human intervention may not be required.
  • the computed differential power resulting from chiller plant optimization implies a decline in chiller plant operation, e.g. breaches a predetermined threshold, a presence of abnormality is ascertained and a notification is generated and provided to an operator to request human intervention, e.g. manual check on physical equipment and/or optimization strategies.
  • This predetermined threshold may be defined as: the computed differential power resulting from chiller plant optimization is a positive value greater than a predetermined value, or becomes an increasingly positive value over a period of time, etc. If abnormality in the computed differential power resulting from chiller plant optimization is ascertained present, the process may proceed to block 405 to re-train the equipment models.
  • the results from block 415 and 417 assist the operator in identifying presence of abnormality in chiller plant optimization and/or equipment and root cause(s) of the abnormality.
  • a representation of optimization strategies or options may be provided as shown in Figure 1 1 .
  • CT approach operator may determine, from the representation and based on real-time weather and cooling tonnage, the CT temperature from 1 to 5 degrees Celsius which will be most efficient, i.e. minimize power.
  • CWP approach operator may determine, from the representation and based on real-time weather and cooling tonnage, the CWP flow which will be most efficient, i.e. minimize power. Accordingly, the LEO system is able to learn from the data and perform autonomous control to achieve the most optimized set points.
  • Equipment performance decomposition-based approach described in Figure 4 can be further reconfigured into many different processes for, but not limited to, performance comparison.
  • One or more time periods of data may be set as baselines for training prediction models as shown in Figures 3B, 3C 3D or 3H, and one or more periods of the data is subset for comparison.
  • Equipment and chiller plant performance comparison can be achieved by applying differential equations 5 and 6, and summation for one or more baselines and other periods of the data.
  • Figure 9 shows an evaluation of chiller plant performance based on a comparison of predicted total chiller plant power 901 and actual total chiller plant power 902 to evaluate the value of improvement.
  • Figure 9 also shows a percentage deviation 903 of actual from predicted total chiller plant power. This deviation 903 refers to the differential power of the chiller plant as mentioned in blocks 415 and 417.
  • the steps described in relation to blocks 41 1 , 413, 415 and/or 417 will be performed based on differential flow parameters, differential temperature and/or differential power.
  • flow and/or temperature parameters may be converted to power parameter as known to person skilled in the art during performance of the steps of blocks 41 1 , 413, 415 and/or 417.
  • FIG. 8 plots the data distribution over cooling tower speed (CT Speed) and cooling tower power, collected in fully controlled chiller plant with a fixed VSD configuration setting (denoted as original data 801 ) and random VSD configuration (denoted as rich data 802) respectively.
  • the cooling tower fan is mainly operated at the speed between 20% to 40% of the maximum speed.
  • Figure 5 shows that the LEO system provides visualization data with targeted areas for human intervention and automatic optimization as compared to existing HVAC Big Data Tools.
  • Figure 6 shows that LEO system performs machine and statistics machine learning to deliver 2 types of results: i) Automatic optimization that results in improved energy efficiency, ii) Provide some very specific actionable information for users to take specific actions.
  • LEO system suggests that the energy efficiency of the chiller 3 is gradually going down by x.xx% since it was serviced 3 months ago. LEO system predicts that restoring the energy efficiency of the chiller to its original conditions would result in a saving of $xxx per months.
  • Figure 12 shows an implementation, but not limited to, an energy or management system (EMS/BMS) for buildings and chiller plants.
  • the invention transforms the existing EMS/BMS from rule-based to a data driven, or a hybrid rule-based and data driven EMS/BMS.
  • the system architecture includes a real time control system 1201 for in- premise control, and a non real time cloud-based system 1202 for data management, machine learning and remote diagnostics.
  • the cloud-based system 1202 or server includes at least one cloud-based computing unit, a memory storage for storing data, e.g.
  • communication module for receiving and/or transmitting data to and/or from the in premise real time control system 1201 , input/output device, e.g. display unit, and other appropriate components.
  • input/output device e.g. display unit, and other appropriate components.
  • the cloud-based computing unit is communicably coupled to the memory storage, communication module, and input/output device, and configured to implement machine learning and/or diagnostics.
  • the in-premise control system 1201 includes sensors and/or actuators 1203 which are communicably coupled to chiller plant equipment for sensing data parameters, e.g. measure speed, flow, temperature and/or power, of equipment and/or for controlling equipment.
  • data parameters e.g. measure speed, flow, temperature and/or power
  • the in-premise control system 1201 further includes energy/building management system 1204 using direct digital controllers (DDCs) or programmable logic controllers (PLCs) with rules for chiller plant, air handling units (AHUs), fan coil units (FCUs), etc.
  • the energy/building management system 1204 may include at least one computing unit which is communicably coupled to the sensors and actuator 1203, directly or indirectly by communication module.
  • the in-premise control 1201 further includes the LEO system 1204 (see also Figure 1 ) which is configured to perform real-time learning, control, optimization and diagnostics.
  • the LEO system 1204 includes at least one memory storage, and at least one computing unit communicably coupled thereto.
  • the memory storage is configured to store data (e.g. baseline data, cross-validation data, test data), prediction models, and computer-executable instructions that, when executed by the at least one computing unit, cause performance of operations as described in the present disclosure and in relation to blocks 401 to 417.
  • the computing unit of the LEO system may be communicably coupled to the sensors and/or actuators 1203, directly or indirectly, to receive measured data transmitted by the sensors and/or actuators 1203.
  • the LEO system 1204 is communicably coupled to the cloud server 1202 for data transmission therebetween, and to at least an input/output device, e.g. display unit and data entry unit, to provide a user interface.
  • the user interface or display unit is configured to display notifications and/or diagnostics from the LEO system 1205, and allow viewing of reports generated by the LEO system 1205.
  • the user interface 1206 or input unit is further configured to allow an operator, e.g. building and/or database manager, provide instructions to control equipment and/or chiller plant.
  • an operator e.g. building and/or database manager

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Testing And Monitoring For Control Systems (AREA)
  • Air Conditioning Control Device (AREA)

Abstract

L'invention concerne un système de gestion d'énergie/de bâtiment guidé par des données, ou reposant sur des règles hybrides et guidé par des données, comme pour des installations de refroidissement, qui présente la capacité d'apprendre à partir des données et d'évaluer les performances. Selon l'invention, un procédé mis en œuvre par ordinateur forme des modèles de prédiction pour chaque modèle d'équipement et modèle d'installation de refroidissement au moyen de données de ligne de base, prédit un paramètre pour chaque modèle d'équipement et modèle d'installation de refroidissement au moyen de données de ligne de base, calcule un paramètre différentiel de chaque équipement sur la base des paramètres prédits et réels de chaque équipement, calcule un paramètre différentiel de l'installation de refroidissement sur la base des paramètres prédits et réels de l'installation de refroidissement, calcule un paramètre différentiel résultant de l'optimisation de l'installation de refroidissement par la soustraction des paramètres différentiels de divers équipements du paramètre différentiel de l'installation de refroidissement, la détermination de la présence d'une anomalie dans le paramètre différentiel résultant de l'optimisation de l'installation de refroidissement et la génération d'une notification si le paramètre différentiel résultant de l'optimisation de l'installation de refroidissement est déterminé comme étant anormal.
PCT/SG2017/050324 2016-06-29 2017-06-29 Modélisation, optimisation et diagnostic d'installations de refroidissement reposant sur un apprentissage machine à grande échelle WO2018004464A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
SG11201810279QA SG11201810279QA (en) 2016-06-29 2017-06-29 Large scale machine learning-based chiller plants modeling, optimization and diagnosis

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
SG10201605346S 2016-06-29
SG10201605346S 2016-06-29

Publications (1)

Publication Number Publication Date
WO2018004464A1 true WO2018004464A1 (fr) 2018-01-04

Family

ID=60787034

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/SG2017/050324 WO2018004464A1 (fr) 2016-06-29 2017-06-29 Modélisation, optimisation et diagnostic d'installations de refroidissement reposant sur un apprentissage machine à grande échelle

Country Status (2)

Country Link
SG (1) SG11201810279QA (fr)
WO (1) WO2018004464A1 (fr)

Cited By (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108664696A (zh) * 2018-04-02 2018-10-16 国家计算机网络与信息安全管理中心 一种冷水机组运行状态的测评方法及装置
WO2019143482A1 (fr) * 2018-01-22 2019-07-25 Siemens Industry, Inc. Système et procédé d'optimisation de performance d'opérations d'installation de refroidisseur d'eau
CN110118426A (zh) * 2019-05-31 2019-08-13 同方泰德国际科技(北京)有限公司 一种适用于地铁车站的冷却塔塔群控制装置
CN110222398A (zh) * 2019-05-29 2019-09-10 广州汇电云联互联网科技有限公司 冷水机组人工智能控制方法、装置、存储介质及终端设备
EP3736646A1 (fr) 2019-05-09 2020-11-11 Siemens Schweiz AG Procédé et organe de commande d'une installation de refroidisseur pour une installation de bâtiment et de refroidisseur
CN112084707A (zh) * 2020-09-02 2020-12-15 西安建筑科技大学 基于冷冻水和冷却水变流量解耦的制冷机房节能优化方法及系统
CN112465230A (zh) * 2020-11-30 2021-03-09 施耐德电气（中国）有限公司 一种自适应的冷水机组开机组合优化的预测方法及系统
WO2021061176A1 (fr) * 2019-09-27 2021-04-01 Nokia Technologies Oy Procédé, appareil et programme informatique de localisation d'équipement utilisateur
CN113221373A (zh) * 2021-05-26 2021-08-06 西安热工研究院有限公司 一种配置多台机力通风冷却塔的循环水冷端系统优化方法和系统
US20210318044A1 (en) * 2018-07-16 2021-10-14 Carrier Corporation System and method for performance estimation of a chiller plant
US11175064B2 (en) 2018-07-18 2021-11-16 Carrier Corporation Analytics based chiller sequencing
US20210398048A1 (en) * 2020-06-19 2021-12-23 Shandong University Method and system for predicting building energy consumption based on holt-winters and extreme learning machine
US11248819B2 (en) 2019-06-05 2022-02-15 Honeywell International Inc. Process for adaptable health, degradation and anomaly detection of systems using benchmarks
US11287191B2 (en) 2019-03-19 2022-03-29 Baltimore Aircoil Company, Inc. Heat exchanger having plume abatement assembly bypass
EP4036820A1 (fr) * 2021-01-28 2022-08-03 Uros AG Appareil pour l'exploitation d'un modèle de maintenance modélisant le stockage de l'eau d'un système de distribution d'eau
EP4036819A1 (fr) * 2021-01-28 2022-08-03 Uros AG Appareil de fonctionnement d'une partie de modélisation de modèle de maintenance d'un système de distribution d'eau
US11732967B2 (en) 2019-12-11 2023-08-22 Baltimore Aircoil Company, Inc. Heat exchanger system with machine-learning based optimization
WO2023193045A1 (fr) * 2022-04-07 2023-10-12 Exergenics Pty Ltd Système de commande d'installation d'eau réfrigérée
US11976882B2 (en) 2020-11-23 2024-05-07 Baltimore Aircoil Company, Inc. Heat rejection apparatus, plume abatement system, and method

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090093892A1 (en) * 2007-10-05 2009-04-09 Fisher-Rosemount Systems, Inc. Automatic determination of the order of a polynomial regression model applied to abnormal situation prevention in a process plant
US20110190946A1 (en) * 2008-08-22 2011-08-04 Charles Ho Yuen Wong Method And System Of Energy-Efficient Control For Central Chiller Plant Systems
US20120083927A1 (en) * 2010-10-01 2012-04-05 Shimizu Corporation Operation Management Apparatus, Operation Management Method, and Operation Management Program
CN103234256A (zh) * 2013-04-17 2013-08-07 上海达希能源科技有限公司 动态负荷跟踪的中央空调冷源全局最优节能控制方法
US20140229146A1 (en) * 2013-02-08 2014-08-14 Entic, Llc In-situ optimization of chilled water plants
CN104566765A (zh) * 2013-10-16 2015-04-29 嘉日国际集团控股有限公司 中央空调整体节能控制方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090093892A1 (en) * 2007-10-05 2009-04-09 Fisher-Rosemount Systems, Inc. Automatic determination of the order of a polynomial regression model applied to abnormal situation prevention in a process plant
US20110190946A1 (en) * 2008-08-22 2011-08-04 Charles Ho Yuen Wong Method And System Of Energy-Efficient Control For Central Chiller Plant Systems
US20120083927A1 (en) * 2010-10-01 2012-04-05 Shimizu Corporation Operation Management Apparatus, Operation Management Method, and Operation Management Program
US20140229146A1 (en) * 2013-02-08 2014-08-14 Entic, Llc In-situ optimization of chilled water plants
CN103234256A (zh) * 2013-04-17 2013-08-07 上海达希能源科技有限公司 动态负荷跟踪的中央空调冷源全局最优节能控制方法
CN104566765A (zh) * 2013-10-16 2015-04-29 嘉日国际集团控股有限公司 中央空调整体节能控制方法

Cited By (23)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2019143482A1 (fr) * 2018-01-22 2019-07-25 Siemens Industry, Inc. Système et procédé d'optimisation de performance d'opérations d'installation de refroidisseur d'eau
CN108664696A (zh) * 2018-04-02 2018-10-16 国家计算机网络与信息安全管理中心 一种冷水机组运行状态的测评方法及装置
US20210318044A1 (en) * 2018-07-16 2021-10-14 Carrier Corporation System and method for performance estimation of a chiller plant
US11175064B2 (en) 2018-07-18 2021-11-16 Carrier Corporation Analytics based chiller sequencing
US11287191B2 (en) 2019-03-19 2022-03-29 Baltimore Aircoil Company, Inc. Heat exchanger having plume abatement assembly bypass
US11506413B2 (en) 2019-05-09 2022-11-22 Siemens Schweiz Ag Method and controller for controlling a chiller plant for a building and chiller plant
EP3736646A1 (fr) 2019-05-09 2020-11-11 Siemens Schweiz AG Procédé et organe de commande d'une installation de refroidisseur pour une installation de bâtiment et de refroidisseur
CN110222398A (zh) * 2019-05-29 2019-09-10 广州汇电云联互联网科技有限公司 冷水机组人工智能控制方法、装置、存储介质及终端设备
CN110222398B (zh) * 2019-05-29 2023-01-13 广州汇电云联互联网科技有限公司 冷水机组人工智能控制方法、装置、存储介质及终端设备
CN110118426A (zh) * 2019-05-31 2019-08-13 同方泰德国际科技(北京)有限公司 一种适用于地铁车站的冷却塔塔群控制装置
US11248819B2 (en) 2019-06-05 2022-02-15 Honeywell International Inc. Process for adaptable health, degradation and anomaly detection of systems using benchmarks
WO2021061176A1 (fr) * 2019-09-27 2021-04-01 Nokia Technologies Oy Procédé, appareil et programme informatique de localisation d'équipement utilisateur
US11732967B2 (en) 2019-12-11 2023-08-22 Baltimore Aircoil Company, Inc. Heat exchanger system with machine-learning based optimization
US11842306B2 (en) * 2020-06-19 2023-12-12 Shandong University Method and system for predicting building energy consumption based on holt-winters and extreme learning machine
US20210398048A1 (en) * 2020-06-19 2021-12-23 Shandong University Method and system for predicting building energy consumption based on holt-winters and extreme learning machine
CN112084707A (zh) * 2020-09-02 2020-12-15 西安建筑科技大学 基于冷冻水和冷却水变流量解耦的制冷机房节能优化方法及系统
US11976882B2 (en) 2020-11-23 2024-05-07 Baltimore Aircoil Company, Inc. Heat rejection apparatus, plume abatement system, and method
CN112465230A (zh) * 2020-11-30 2021-03-09 施耐德电气（中国）有限公司 一种自适应的冷水机组开机组合优化的预测方法及系统
EP4036819A1 (fr) * 2021-01-28 2022-08-03 Uros AG Appareil de fonctionnement d'une partie de modélisation de modèle de maintenance d'un système de distribution d'eau
EP4036820A1 (fr) * 2021-01-28 2022-08-03 Uros AG Appareil pour l'exploitation d'un modèle de maintenance modélisant le stockage de l'eau d'un système de distribution d'eau
CN113221373B (zh) * 2021-05-26 2023-03-14 西安热工研究院有限公司 一种配置多台机力通风冷却塔的循环水冷端系统优化方法和系统
CN113221373A (zh) * 2021-05-26 2021-08-06 西安热工研究院有限公司 一种配置多台机力通风冷却塔的循环水冷端系统优化方法和系统
WO2023193045A1 (fr) * 2022-04-07 2023-10-12 Exergenics Pty Ltd Système de commande d'installation d'eau réfrigérée

Also Published As

Publication number Publication date
SG11201810279QA (en) 2018-12-28

Similar Documents

Publication Publication Date Title
WO2018004464A1 (fr) Modélisation, optimisation et diagnostic d'installations de refroidissement reposant sur un apprentissage machine à grande échelle
EP3679773B1 (fr) Optimisation d'énergie d'unité de refroidissement par l'intermédiaire d'une commande intelligente de point de consigne de température d'air d'alimentation
US10521490B2 (en) Equipment maintenance management system and equipment maintenance management method
US20170227950A1 (en) Production control system and integrated production control system
Orchard et al. A particle filtering approach for on-line failure prognosis in a planetary carrier plate
Cattaneo et al. A digital twin proof of concept to support machine prognostics with low availability of run-to-failure data
US11556484B2 (en) Minimizing energy consumption by peripheral machines
CN111684369B (zh) 用于风扇或风扇总成的优化操作的方法
US20210033097A1 (en) Method for optimizing the efficiency and/or the running performance of a fan or a fan arrangement
WO2020120115A1 (fr) Prédictions pour un processus dans une installation industrielle
Horrigan et al. A statistically-based fault detection approach for environmental and energy management in buildings
WO2019162648A1 (fr) Diagnostic de système de commande
CN116193819B (zh) 一种数据中心机房节能控制方法、系统、装置及电子设备
Alamaniotis et al. Anticipatory monitoring and control of complex energy systems using a fuzzy based fusion of support vector regressors
Biemann et al. Data Center HVAC Control Harnessing Flexibility Potential via Real-Time Pricing Cost Optimization Using Reinforcement Learning
CN115335836A (zh) 训练针对工业应用的人工智能模块
Pinto End-effector tools wear prediction: a multimodel approach
Shi et al. Using Building Performance Simulation for Fault Impact Evaluation
Berka et al. Effective maintenance of stochastic systems via dynamic programming
Vachtsevanos et al. A novel approach to integrated vehicle health management
RU2796809C2 (ru) Способ оптимизированной эксплуатации вентилятора или вентиляторной системы
Angadi et al. Regressive Event-Tracker: A Causal Prediction Modelling of Degradation in High Speed Manufacturing
AU2021105481A4 (en) Construction operation, monitoring, maintenance planning and future risk prediction of bigger constructions using Artificial Intelligence based Internet of things
US11899440B2 (en) Remote monitoring
Rawat et al. Condition based optimal maintenance strategy for multi-component system

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 17820674

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 17820674

Country of ref document: EP

Kind code of ref document: A1