The present disclosure relates to control of building systems using automated means. More specifically, the present disclosure relates to an automated method of deconstructing a graph representing building systems equipment and connections into sub-systems. The present disclosure particularly addresses the control and automation of HVAC, energy, lighting, irrigation systems, and the like.
Modern buildings contain a varied and complex set of systems for managing and maintaining the building environment. Building automation systems are used to automate the control of many separate systems, such as those used for lighting, climate, security, entertainment, etc. Building automation systems can perform a number of functions, such as automation of equipment scheduling, monitoring of various building parameters, optimization of resource consumption, event or alarm reporting and handling, and many others.
Building automation system implementation requires programmatic understanding of what equipment is available to the building automation system and how that equipment may be utilized. For example, the building automation system needs to account for information such as what equipment can be run simultaneously, what groups of equipment work together to achieve a particular objective, etc. Automatic discovery of this information is challenging with current methodologies.
The present disclosure provides a method of automatically decomposing a complex graph of connected equipment into equipment sub-systems for the purpose of automatic labeling of automatable systems, sub-system, and the equipment therein for machine-driven control. Further the present disclosure relates to user interfaces that allow a user to draw a graph of equipment having n-complexity and n-number of routing paths, and decompose that drawing into a controllable system of atomic sub-systems automatically.
The present disclosure describes a method for the decomposition of sub-systems to automatically infer controllability, ranking, prioritization, and analyzing the sub-systems to identify those that are unique and complete, categorizing sub-systems into synchronous groups (in which only a single sub-system can operate at a time), and asynchronous groups (in which more than one sub-system can operate simultaneously).
The present disclosure details how building automation system would automatically provide semantic labeling for the sub-system and its equipment for retrieval during an analytic stage.
The present disclosure also relates to the automatic reduction of state space in a n-complexity graph of equipment. By using the semantic labeling together with the deconstructed set of meaningful sub-systems, the meaningful control state space of the system can be derived.
There has thus been outlined, rather broadly, the features of the disclosure in order that the detailed description thereof that follows may be better understood and in order that the present contribution to the art may be better appreciated.
Numerous objects, features and advantages of the present disclosure will be readily apparent to those of ordinary skill in the art upon a reading of the following detailed description of presently preferred, but nonetheless illustrative, embodiments of the present disclosure when taken in conjunction with the accompanying drawings. The disclosure is capable of other embodiments and of being practiced and carried out in various ways. Also, it is to be understood that the phraseology and terminology employed herein are for the purpose of descriptions and should not be regarded as limiting.
Although specific embodiments have been illustrated and described herein, it will be appreciated by those of ordinary skill in the art that any arrangement, which is calculated to achieve the same purpose, may be substituted for the specific embodiment shown. This application is intended to cover any adaptions or variations of the present disclosure.
This section summarizes some aspects of the present disclosure and briefly introduces some preferred embodiments. Simplifications or omissions in this section as well as in the abstract or the title of this description may be made to avoid obscuring the purpose of this section, the abstract, and the title. Such simplifications or omissions are not intended to limit the scope of the present disclosure nor imply any limitations.
Several advantages of one or more aspects of the present disclosure include but are not limited to: to generate a system control scheme automatically from a complex equipment graph; to decompose automatically the equipment graph into sub-system sets, where the decomposition enables the generation of a system control scheme; to enable automatic semantic reasoning about the generation of said system control scheme from the decomposition, thereby enabling more efficient generation of the control scheme as well as increasing human reasoning of the control scheme generation process; to automatically select valid and unique equipment sub-systems from said decomposition, thereby reducing the control scheme search space so as to increase control path search efficiency; to enable automatic prioritization of sub-systems, thereby enabling the generation of a system control scheme that responds to system preferences and priorities; to classify automatically sub-systems as either asynchronous or synchronous, thereby enabling the generation of a control scheme that responds to precedence and sequential operation limitations of particular equipment and sets of equipment. Other advantages of one or more aspects of the disclosed method will be apparent from consideration of the following drawings and description.
To further clarify various aspects of some example embodiments of the present disclosure, a more particular description of the disclosure will be rendered by reference to specific embodiments thereof that are illustrated in the appended drawings. It is appreciated that the drawings depict only illustrated embodiments of the disclosure and are therefore not to be considered limiting of its scope. The disclosure will be described and explained with additional specificity and detail through the use of the accompanying drawings in which:
The following conventions are used for reference numerals: the first digit indicates the figure in which the numbered part first appears (the first two digits are used for the figure number when required). The remaining digits are used to identify the part in the drawing.
The embodiments of the present disclosure described below are not intended to be exhaustive or to limit the disclosure to the precise forms disclosed in the following detailed description. Rather, the embodiments are chosen and described so that others skilled in the art may appreciate and understand the principles and practices of the present disclosure.
The following embodiments and the accompanying drawings, which are incorporated into and form part of this disclosure, illustrate embodiments of the disclosure and together with the description, serve to explain the principles of the disclosure. To the accomplishment of the foregoing and related ends, certain illustrative aspects of the disclosure are described herein in connection with the following description and the annexed drawings. These aspects are indicative, however of, but a few of the various ways in which the principles of the disclosure can be employed and the subject disclosure is intended to include all such aspects and their equivalents. Other advantages and novel features of the disclosure will become apparent from the following detailed description of the disclosure when considered in conjunction with the drawings.
Explanation will be made below with reference to the aforementioned figures for illustrative embodiments concerning the present invention.
The present disclosure describes a method of decomposing a system of interconnected equipment into various sets of equipment comprising various sub-systems. The basic structure of such a sub-system 100 is shown in
In various embodiments, an equipment sub-system 100 transport 104 may use various means. As shown in
A sub-system is classified as synchronous when said sub-system routing paths are conjoined in an manner that only one sub-system may operate at a time; and a sub-system is classified as asynchronous when said sub-system routing paths are conjoined in a manner that two or more sub-systems may operate at the same time.
The decomposition process of a system may be accomplished by recognizing and extracting sub-systems from the system graph. Sub-system reduction to atomic sub-systems having a known equipment topology enable a machine learning engine to reason about the system and control the system in a uniform expected manner. (
The decomposition process may also recognize characteristics of or relationships between sub-systems, such as deriving sub-system or branch type. The process may identify the sub-system as either synchronous or asynchronous based on the equipment and sub-system characteristics and capabilities. The process may also identify sub-systems with attributes like priority and precedence. For example, sub-systems may be organized in asynchronous and synchronous groups.
The process may also organize the whole deconstructed graph of systems, sub-systems, and equipment into structured maps, trees, or sets which can represent unions based on asynchronous and synchronous groups, or other characteristics.
Application of the methodology may yield sets of equipment that constitute the various sub-systems in the given system.
Having executed the decomposition process, the sub-systems comprising a particular system may be classified.
As part of the decomposition process, sub-systems may be classified as either asynchronous or synchronous.
A controlled system 702 may have any number of groups of sub-systems 706 representing any number and variety of characteristics. An illustration of one embodiment of how equipment sub-systems 706 may be grouped 704 and classified is shown in
A controlled system 500 having multiple sub-systems 501, 502, 503, 504, 505 can further be deconstructed in such a way that the equipment or system states required to initialize the sub-system 501, 502, 503, 504, 505 are pre-computed. An embodiment is shown in
Another embodiment of the present disclosure is for the purpose of semantic extraction. By decomposing systems into atomic sub-systems comprising the necessary components of source, sink, and transport, a control system may automatically control and manage these system components in a rule-based way. The controller may also apply meaning to a sub-system by means of classification or rule tables. These classifications and/or rules may be used to generate semantics for the system, the sub-systems, and the constituent parts. An embodiment can be seen in
A graphical user interface 802 may be used to input or drive the creation of an equipment graph 804, such that an electronic device having a screen may be used to automatically deconstruct a controllable system from the graphical representation 802 of the controllable system, the equipment objects, sets, priority, and their relationships. An embodiment of such a device can be seen in
In some graphical user interface 802 embodiments having an electronic display, a user may drag and drop or instantiate equipment objects from an equipment object library 902 into a system drawing 904 on a drawing screen 906, either on a touchscreen, cursor driven input device, or other means. An embodiment can be seen in
These drawings 904, made in situ or a-priori, can be disaggregated using the above methods into a graph 804 of sub-systems, priority, sub-system synchronicity, labeling, and the underlying control knowledge required to control the system in an unsupervised manner. An embodiment can be seen in
These deconstructed graphs 804 of sub-system 1002 and their semantic labeling 1004 can be used to generate automatic analytics 1008, 1010, 1012, 1014 as in the embodiment in
In some embodiments, the sub-system semantics 1004 may provide analytic display or graph grouping of equipment automatically, as in the embodiment in
The foregoing disclosure describes some possible embodiments of this invention, with no indication of preference to the particular embodiment. A skilled practitioner of the art will find alternative embodiments readily apparent from the previous drawings and discussion and will acknowledge that various modifications can be made without departure from the scope of the invention disclosed herein.
Number | Name | Date | Kind |
---|---|---|---|
4385384 | Rosbury | May 1983 | A |
5224648 | Simon et al. | Jul 1993 | A |
5519834 | Kamerman | May 1996 | A |
6119125 | Gloudeman et al. | Sep 2000 | A |
6967565 | Lingemann | Nov 2005 | B2 |
7010789 | Kimelman et al. | Mar 2006 | B1 |
7302362 | Misra | Nov 2007 | B2 |
9020647 | Johnson et al. | Apr 2015 | B2 |
9035479 | Gates | May 2015 | B1 |
9258201 | McCoy et al. | Feb 2016 | B2 |
9298197 | Matsuoka et al. | Mar 2016 | B2 |
9557750 | Gust et al. | Jan 2017 | B2 |
9664400 | Wroblewski et al. | May 2017 | B2 |
10705492 | Harvey | Jul 2020 | B2 |
10708078 | Harvey | Jul 2020 | B2 |
20020152298 | Kikta et al. | Oct 2002 | A1 |
20050097161 | Chiou | May 2005 | A1 |
20060106530 | Horvitz et al. | May 2006 | A1 |
20070055392 | D'Amato | Mar 2007 | A1 |
20080082183 | Judge | Apr 2008 | A1 |
20140016572 | Porat et al. | Jan 2014 | A1 |
20140277765 | Karimi et al. | Sep 2014 | A1 |
20140288890 | Khainson | Sep 2014 | A1 |
20140330611 | Steven | Nov 2014 | A1 |
20140358291 | Wells et al. | Dec 2014 | A1 |
20150025917 | Stempora | Jan 2015 | A1 |
20150066229 | Lacroix et al. | Mar 2015 | A1 |
20150112497 | Steven et al. | Apr 2015 | A1 |
20160016454 | Yang et al. | Jan 2016 | A1 |
20160179075 | Shin et al. | Jun 2016 | A1 |
20160201934 | Hester et al. | Jul 2016 | A1 |
20170076206 | Lastras-Montano et al. | Mar 2017 | A1 |
20170103483 | Drees et al. | Apr 2017 | A1 |
20170171580 | Hirsch | Jun 2017 | A1 |
20170289191 | Thioux | Oct 2017 | A1 |
20170315696 | Jacobson | Nov 2017 | A1 |
20170329289 | Kohn | Nov 2017 | A1 |
20180335759 | Harvey | Nov 2018 | A1 |
Entry |
---|
Massif, N., Kaji, S., & Sabrouin, R. (Jul. 2005). Optimization of HVAC control system strategy using two-objective genetic algorithm, Journal of HVAC&R Research, 11(3), 459-486. (Year: 2005). |
Sushanek, F., Kasneci, G., & Weikum, G. (May 2007). YAGO: A core of semantic knowledge unifying WordNet and Wikipedia, WWW 2007, 1-10. (Year: 2007). |
Maasoumy, M., Pinto, A., & Sangiovanni-Vincentelli, A, (2001) Model-based hierarchical optimal control design for HVAC systems, Proceedings of the ASME 2011 Dynamic Systems and Control Conference, 1-8. (Year: 2011). |
Bordes, A., Weston, J., Collobert, R., & Bengio, Y. (Aug. 2011). Learning structured embeddings of knowledge bases, Proceedings of the Twenty-Fifth AAAI Conference on Artificial Intelligence, 1-6. (Year: 2011). |
Nickel, M., Tresp, V., & Kriegel, H. (2011). A three-way model for collective learning on multi-relational data, Proceedings of the 28th International Conference on Machine Learning, 1-8. (Year: 2011). |
Socer, R., Chen, D., Manning, C., & Ng, A. (Jan. 2013) Reasoning with neural tensor networks for knowledge base completion, 1-10. (Year: 2013). |
Berant, L., Chou, A., Frostig, R., & Ling, P. (Oct. 2013). Semantic parsing on Freebase from question-answer pairs, Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, 1533-1544. (Year 2013). |
Bordes, A., Usunier, N., Garcia-Duran, A., Weston, J., & Yakhenko, O. (Apr. 2013). Irreflexive and hierarchical relations as translations, 1-5. (Year: 2013). |
Bordes, A., Usunier, N., Garcia-Duran, A., Weston, J., & Yakhenko, O. (Dec. 2013). Translating embeddings for modeling multi-relational data, Neural Information Processing Systems (NIPS), 1-9. (Year: 2013). |
Chang, K., Yih, W., & Meek, C. (Oct. 2013) Multi-relational latent semantic analysis, Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 1-11. (Year: 2013). |
Weston, J., Bords, A., Yakhnenko, O, & Usunier, N. (Jul. 2013). Connecting language and knowledge bases with ambedding models for relation extraction, 1-6 (Year: 2013). |
Min, B., Grisham, R., Wan, L., Wang, C., & Gondex, D. (Jun. 2013). Distant supervision for relation extraction with an incomplete knowledge base, Proceedings of NAACL-HLT 2013, 777-782. (Year 2013). |
Wang, Z., Zhang, J., Feng, J., & Chen, Z. (2014). Knowledge graph embedding by translating on hyperplanes, Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence, 1112-1119. (Year: 2014). |
Yang, B., Yih, W., He, X., Gao, J., & Deng, L. (Dec. 2014). Embedding entities and relations for learning and inference in knowledge bases, 1-12. (Year: 2014). |
Bordes, A., Glorot, X., Weston, J., & Bengio, Y. (2014). A semantic matching energy function for learning with multi-relational data, Machine Learning, 94(2), 233-259. (Year: 2014). |
Lin, Y, Liu, Z., Sun, M., Liue, Y., & Zhu, X. (2015). Learning entity and relation embeddings for knowledge graph completion, in Proceedings of AAAI'15, 1-7. (Year: 2015). |
He, H., Balakrishnan, A., Eric, M., & Liang, P. (Apr. 2017). Learning symmetric collaborative dialogue agents with dynamic knowledge graph embeddings, 1-11. (Year: 2017). |
Carl-Eric Hagentoft, Assessment Method of Numerical Prediction Models for Combined Heat, Air and Moisture Transfer in Building Components: Benchmarks for One-dimensional Cases, Apr. 2004, Journal of Thermal Env. & Bldg. Sci., VI. 27, No. 4 (Year: 2004). |
BigLadder Software, Occupant Thermal Comfort: Engineering Reference, 2014, The Board of Trustees of the University of Illinois and the Regents of the University of California through the Ernest Orlando Lawrence Berkeley National Labaratory (Year: 2014). |
ANSI/ASHRAE Standard 55-2013: Thermal Environmental Conditions for Human Occupancy, ASHRAE, 2013. |
De Dear, et at., “Developing an Adaptive Model of Thermal Comfort and Preference,” ASHRAE Transactions 1998, vol. 104, Part 1. |
Gagge et al., “An Effective Temperature Scale Based on a Simple Model of Human Physiological Regulatory Response,” ASIYRAE Semiannnual Meeting in Philadelphia, Pennsylyania, Jan. 24-28, 1971. |
Gagge, et. al., A Standard Predictive index of Human Response to the Thermal Environment, ASHRAE Transactions 1986, Part 2B. |
Medhi, et al.,Jan. 2011, “Model-Based Hierarchical Optimal Control Design for HVAC Systems,” ASME 2011 Dynamic Systems and Control Conference and Bath/ASME Symposium on Fluid Power and Motion Control. |
Nakahara, “Study and Practice on HVAC System Commissioning,” The 4th international Symposium on HVAC, Beijing, China, Oct. 9-11, 2003. |
Nassif, et al., “Self-tuning dynamic models of HVAC system components”, Energy and Buildings 40 (2008) 1709-1720. |
Nassif, Nabil, (2005), Optimization of HVAC control system strategy using two-objective genetic algorithm [microform]. |
Qin et al., “Commissioning and Diagnosis of VAV Air-Conditioning Systems,” Proceedings of the Sixth International Conference for Enhanced Building Operations, Shenzhen, China, Nov. 6-9, 2006. |
Salsbury et al., “Automated Testing of HVAC Systems for Commissioning,” Laurence Livermore National Laboratory, 1999, LBNL-43639. |
Vaezi-Nejad, H.; Salsbury, T.; Choiniere, D. (2004). Using Building Control System for Commissioning. Energy Systems Laboratory (http://esl.tamu.edu); Texas A&M University (http://www.tamu.edu). Available electronically from http : / /hdl .handle .net /1969 .1 /5060. |
Welsh, “Ongoing Commissioning (OCx) with BAS and Data Loggers,” National Conference on Building Commissioning: Jun. 3-5, 2009. |
Xiao et al., “Automatic Continuous Commissioning of Measurement Instruments in Air Handling Units,” Building Commissioning for Energy Efficiency and Comfort, 2006, vol. VI-1-3, Shenzhen, China. |
U.S. Appl. No. 15/986,746 Office Action dated Mar. 25, 2020. |
U.S. Appl. No. 15/986,746 Office Action dated Aug. 7, 2019. |
U.S. Appl. No. 15/995,019 Final Office Action dated Apr. 15, 2020. |
U.S. Appl. No. 15/995,019 Office Action dated Jul. 26, 2019. |
U.S. Appl. No. 16/008,713 Final Office Action dated Jun. 18, 2020. |
U.S. Appl. No. 16/008,713 Office Action dated Nov. 1, 2019. |
U.S. Appl. No. 16/921,903 Notice of Allowance, dated Mar. 16, 2022. |
Number | Date | Country | |
---|---|---|---|
20200336328 A1 | Oct 2020 | US |
Number | Date | Country | |
---|---|---|---|
62518745 | Jun 2017 | US |
Number | Date | Country | |
---|---|---|---|
Parent | 16007963 | Jun 2018 | US |
Child | 16921924 | US |