EP4437285A1 - Verfahren zur fehlerprädiktion in einer hvac-anlage - Google Patents
Verfahren zur fehlerprädiktion in einer hvac-anlageInfo
- Publication number
- EP4437285A1 EP4437285A1 EP22800277.0A EP22800277A EP4437285A1 EP 4437285 A1 EP4437285 A1 EP 4437285A1 EP 22800277 A EP22800277 A EP 22800277A EP 4437285 A1 EP4437285 A1 EP 4437285A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- hvac system
- error
- weather
- fault
- probability
- Prior art date
- Legal status (The legal status 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 status listed.)
- Withdrawn
Links
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/89—Arrangement or mounting of control or safety devices
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F2110/00—Control inputs relating to air properties
- F24F2110/10—Temperature
- F24F2110/12—Temperature of the outside air
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F2110/00—Control inputs relating to air properties
- F24F2110/20—Humidity
- F24F2110/22—Humidity of the outside air
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F2130/00—Control inputs relating to environmental factors not covered by group F24F2110/00
- F24F2130/10—Weather information or forecasts
Definitions
- the invention relates to a method for predicting weather-related faults in an HVAC system.
- the method includes in particular the determination of a probability of occurrence of a fault based on a comparison of weather forecasts with stored external conditions, the method enabling an early, individual and simple possibility of fault prediction.
- An object of the invention is to provide a method that makes it possible to easily predict weather-related faults in an HVAC system at an early stage.
- the method should be individually applicable to HVAC systems of different types and configurations.
- independent claim 1 and independent claim 15 are directed to particular embodiments of the invention.
- HVAC systems in which weather-related faults are indicated have a high probability of exhibiting that fault again in similar weather conditions that occur again.
- a method for predicting weather-related faults in an HVAC system therefore comprises the step (a) of monitoring a history of faults in the HVAC system.
- monitoring the error history enables an individual prediction regardless of the type, installation situation and use of the system, since the error history can be recorded individually for each HVAC system.
- the method according to the invention for predicting weather-related faults in an HVAC system also includes the step (b) of storing external conditions at the time of a respective fault.
- the method according to the invention can additionally include storing an error type with an assessment of the dependence of the respective error on the external conditions.
- Such an evaluation can include, for example, the strength of the influence (scoring) of the external conditions on the occurrence of the respective fault and can be used in addition to determining the probability of fault occurrence described below.
- error type is to be interpreted broadly and can, for example, describe the type of error that has occurred, such as depending on the temperature or also depending on the temperature and humidity.
- the evaluation can then also include a differentiated scoring, for example a high scoring for the temperature and a low scoring for the humidity.
- a specific error designation can also be included based on the design of the HVAC system, for example critical cycle behavior, overheating or glacial ice formation.
- the monitoring of the error history and the storage of the external conditions at the time of a respective error can be carried out manually by the input of a technician, by a control unit in the HVAC system or via an interface using an external computing unit.
- the method according to the invention is not restricted in this regard. On In this way, the method can advantageously be implemented individually on HVAC systems of different types and configurations.
- the described storage of the fault type together with the assessment of the dependency on the external conditions can be carried out by a technician on the HVAC system itself, for example via an application (app).
- a fault type can also be stored with an evaluation of the dependence of the respective fault on the external conditions, preferably weather conditions, but can also be carried out by a control unit in the HVAC system or via an interface using an external computing unit.
- a time profile of the external conditions can be stored over a predetermined period of time ⁇ t up to the time of the respective fault.
- the length of the period ⁇ t before an error (trouble) occurs is not limited herein.
- the time period ⁇ t can, for example, cover a short period of time of 1 hour to 8 hours, preferably 2 hours to 6 hours, particularly preferably 3 hours to 4 hours. However, the period can also be 2 to 4 days, preferably 3 days.
- Such a so-called observation period advantageously makes it possible to make an early prediction about the possible occurrence of a fault, since not only the external conditions relating to a specific point in time, but also profiles over a predefined period of time can be stored and used for the prediction.
- the acquisition rate of the outdoor conditions within the period At. Outside conditions can, for example, be recorded and saved every hour, every half hour, but also at longer intervals within the observation period.
- external conditions can be any conditions that occur in the external environment of the system due to a current weather situation, such as wind speed, UV index, temperature and humidity.
- the external conditions can include a temperature and/or an air humidity. This can, for example, by means of individual sensors or by means of a combined sensor for temperature and humidity are measured.
- the sensor or sensors can be provided in the environment of the HVAC system or in the HVAC system itself.
- information about the installation location of the HVAC system can also be stored.
- the installation location can include the geographic installation location, the installation location in relation to a building, e.g. basement or outdoor area, and information about the structural condition of the installation location, such as insulation, and/or the installation height of the HVAC system.
- the external conditions can include weather conditions at the installation site of the HVAC system.
- the method according to the invention for predicting weather-related faults in an HVAC system also includes step (c) of monitoring weather forecasts and determining a fault occurrence probability using an external processor based on a comparison of the weather forecasts with the stored external conditions.
- external computing unit is to be interpreted broadly herein.
- An external processing unit can, for example, include configurations starting from a terminal device connected directly by cable through to a data center (cloud) connected via a network.
- the external computing unit is particularly preferably a cloud.
- the weather forecasts can be monitored based on the installation location of the HVAC system.
- the error occurrence probability can be determined based on the extraction of data points from multivariate time series of external conditions of the same duration and resolution. For example, the error occurrence probability can be determined as follows:
- Multivariate time series of weather data e.g. temperature, relative humidity, UV index and/or wind speeds
- a data point of time-independent properties is extracted via suitable aggregation (e.g. mean temperature, maximum increase in humidity, maximum wind speed).
- suitable distance metric for example Euclidean
- the metric can be adjusted to different error types using weights, so that for a temperature-dependent error, a higher weight (e.g. via scoring) is placed on the temperature dimension of the data points and two weather conditions are considered to be more similar the more similar the temperatures ( or their change) of these two weather conditions.
- a suitable clustering method can be used to assign a corresponding cluster center point for each weather-dependent fault, and the distance of a data point from the cluster center point of a fault reflects the probability of this fault occurring (the smaller the distance, the more likely the fault is).
- the method according to the invention for predicting weather-related errors in an HVAC system also includes step (d) of deriving a prediction for the occurrence of a weather-related error in the HVAC system by the external computing unit using a threshold value for the error occurrence probability.
- a threshold value of 0.5 can be defined for a probability of error occurrence between 0 (error does not occur again) and 1 (error occurs again). If the threshold value is exceeded, the prediction can then be that the error will occur again and if it falls below that the error will not occur again.
- the threshold value can be individually adjusted, and the prediction can be adjusted differentiated for different values above the threshold value.
- the external computing unit can comprise at least one server and at least one application, and steps (c) and (d) can be carried out using the at least one application, with optional step (c) determining the probability of error occurrence using machine learning can be determined.
- an error warning for the HVAC system can be issued if the ascertained probability of the occurrence of an error exceeds the threshold value.
- a warning can be issued via an application (app).
- an application app
- such a warning can also be given visually or audibly, for example on the system itself.
- a message can be sent to a technician if the ascertained probability of occurrence of the error exceeds the threshold value. For example, a high-pressure fault cannot be avoided when there is high humidity in summer or when temperatures are very cold. If the determined error occurrence probability exceeds the threshold value, i.e. if it is considered likely that the error will occur again, the technician can be notified to wait another day, since the error is probably not permanent. In the event of a high-pressure disruption in the transitional period, on the other hand, the message can be given to carry out an operation.
- a control intervention in the HVAC system can take place if the ascertained probability of occurrence of a fault exceeds the threshold value.
- a control intervention can, for example, include the adjustment of operating parameters, such as the parameters for the storm mode in the case of a gas wall unit or an extension of the defrosting time in the case of a heat pump and/or switching on an electric heater when glacier ice forms.
- the time profile of at least one operating parameter of the HVAC system can be stored over a predetermined period At up to the time of the respective error, in which case in step (c) the Error probability can also be determined based on the stored history of at least one operating parameter.
- the Error probability can also be determined based on the stored history of at least one operating parameter.
- HVAC system can be a gas wall unit or a heat pump. According to a preferred embodiment, however, the HVAC system can in particular be a heat pump.
- a system according to the invention for predicting weather-related errors in an HVAC system comprises an HVAC system with a control device and an interface, and an external processing unit which is connected to the HVAC system via the interface, the system for carrying out the method described herein is set up.
- system according to the invention can each additionally comprise an individual or a combined temperature sensor and air humidity sensor.
- FIGS. 1 to 4 schematically show embodiments of the method according to the invention and of the system according to the invention.
- FIG. 1 shows schematically one embodiment of a system for predicting weather-related faults in an HVAC system.
- FIGS. 4a and 4b schematically show an embodiment of a method for predicting weather-related faults for an HVAC system configured as a gas wall unit.
- FIG. 1 shows a schematic representation of an embodiment of a system according to the invention for predicting weather-related faults in an HVAC system.
- the system 100 shown in FIG. 1 includes an HVAC system 101 with a control device and an interface (not shown), as well as an external computing unit 102, designed as a cloud in the embodiment in FIG.
- the external computing unit 102 is connected to the HVAC system via the interface 104.
- step (b) of the method according to the invention external conditions at the time of a respective fault in the HVAC system 101 are stored. Depending on the type and design of the HVAC system 101, this can also be done manually by the input of a technician, by the control unit in the HVAC system 101 or via the connection 104 to the external computing unit 102 using the interface of the HVAC system 101.
- the system 100 can additionally include a single temperature sensor 106 and air humidity sensor 107 in each case.
- the system 100 can also include a combined temperature sensor and humidity sensor.
- FIGS. 4a and 4b there are correspondingly discrete values for the temperature and wind speed in a gas wall device 300, which can be determined by means of corresponding sensors.
- the acquisition rate of the external conditions within the observation period At is also not restricted.
- outside conditions can be recorded every hour, every half hour, but also at longer intervals within the observation period.
- Corresponding curves 201, 202, 301, 302 can then be created on the basis of the detected discrete values.
- step (c) of the method according to the invention for predicting weather-related faults in an HVAC system weather forecasts 103 are monitored and a fault occurrence probability is determined by the external computing unit 102 using a comparison of the weather forecasts 103 with the stored external conditions.
- FIGS. 3a and 3b show the method as an example for an HVAC system configured as a heat pump 200.
- Figures 4a and 4b show this as an example for an HVAC system designed as a gas wall unit 300 .
- the wind speed is considered analogously 301, 308.
- a forecast for the occurrence of a weather-related fault in the HVAC system is derived by the external computing unit using a threshold value for the fault occurrence probability.
- a threshold value of 0.5 can be defined for a probability of error occurrence between 0 (error does not occur again) and 1 (error occurs again). If the threshold value is exceeded, the prediction can then be that the error will occur again and if it falls below that the error will not occur again.
- the threshold value can be individually adjusted, and the prediction can be adjusted differently for different values above the threshold value.
- the external computing unit can comprise at least one server and at least one application, and steps (c) and (d) can be carried out using the at least one application, with optional step (c) determining the probability of error occurrence using machine learning can be determined.
- an error warning for the HVAC system 101 can be output 105 if the ascertained probability of the occurrence of an error exceeds the threshold value.
- a warning can be issued via an application (app).
- an application app
- such a warning can also be visual or audible, for example on the HVAC system itself.
- a message can be sent 105 to a technician if the ascertained probability of the occurrence of an error exceeds the threshold value. For example, a high-pressure fault cannot be avoided when there is high humidity in summer or when temperatures are very cold. If the ascertained error occurrence probability exceeds the threshold value, ie if it is considered likely that the error will occur again, the technician can be notified, one day later wait and see as the error is unlikely to be permanent. In the event of a high-pressure disruption in the transitional period, on the other hand, the message can be given to carry out an operation.
- a control intervention 105 can take place in the HVAC system 101 if the ascertained probability of the occurrence of a fault exceeds the threshold value.
- a control intervention 105 can include, for example, the adjustment of operating parameters, such as the parameters for the storm mode in the case of a gas wall device or an extension of the defrosting time in the case of a heat pump and/or switching on an electric heater when glacier ice forms.
- step (c) calculates the probability of the error occurring can also be determined using the stored history of the at least one operating parameter.
- step (c) calculates the probability of the error occurring can also be determined using the stored history of the at least one operating parameter.
- a user profile can advantageously be created and used to determine the probability of an error occurring. If, for example, the running time and the performance of a heat pump in the monitored period are compared with the stored data, this comparison can be used to improve the accuracy of the forecast to the effect that similar weather and similar heating requirements result in a similar user profile, and thus at the time of the forecast weather conditions comparable running time and performance can be assumed.
- the invention has numerous advantages.
- the method according to the invention and the system according to the invention offer a simple possibility of error prediction.
- An error prediction can be made early, ie the advance warning time is correspondingly long in contrast to methods, for example in a heat pump, which can detect glacial ice formation, but only when it has started.
- the method according to the invention and the system according to the invention offer an individual solution for each HVAC system since a fault history is used for the prediction for each individual system.
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Air Conditioning Control Device (AREA)
Abstract
Description
Claims
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| DE102021130996.4A DE102021130996A1 (de) | 2021-11-25 | 2021-11-25 | Verfahren zur fehlerprädiktion in einer hvac-anlage |
| PCT/EP2022/078192 WO2023094064A1 (de) | 2021-11-25 | 2022-10-11 | Verfahren zur fehlerprädiktion in einer hvac-anlage |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| EP4437285A1 true EP4437285A1 (de) | 2024-10-02 |
Family
ID=84246159
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| EP22800277.0A Withdrawn EP4437285A1 (de) | 2021-11-25 | 2022-10-11 | Verfahren zur fehlerprädiktion in einer hvac-anlage |
Country Status (3)
| Country | Link |
|---|---|
| EP (1) | EP4437285A1 (de) |
| DE (1) | DE102021130996A1 (de) |
| WO (1) | WO2023094064A1 (de) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2636080A (en) * | 2023-11-24 | 2025-06-11 | Octopus Energy Heating Ltd | Heating installations, methods and systems |
| EP4733865A1 (de) | 2024-10-22 | 2026-04-29 | Siemens Schweiz AG | Verfahren zum bereitstellen eines gebäudegerätemodells, verfahren zum nutzen eines gebäudegerätemodells, gebäudegerätemodell |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3268821B1 (de) * | 2015-03-11 | 2020-07-15 | Siemens Industry, Inc. | Kaskadierte identifizierung in gebäudeautomation |
| US10969775B2 (en) * | 2017-06-23 | 2021-04-06 | Johnson Controls Technology Company | Predictive diagnostics system with fault detector for preventative maintenance of connected equipment |
| US10845079B1 (en) | 2017-06-28 | 2020-11-24 | Alarm.Com Incorporated | HVAC analytics |
| CN107679649A (zh) * | 2017-09-13 | 2018-02-09 | 珠海格力电器股份有限公司 | 一种电器的故障预测方法、装置、存储介质及电器 |
| CA3090718C (en) * | 2018-02-19 | 2023-01-03 | BrainBox AI Inc. | Systems and methods of optimizing hvac control in a building or network of buildings |
| CN111578444A (zh) * | 2019-02-19 | 2020-08-25 | 珠海格力电器股份有限公司 | 一种空调故障预测方法、装置、存储介质及空调 |
| CN109974220B (zh) | 2019-04-01 | 2020-06-16 | 珠海格力电器股份有限公司 | 电器设备的控制方法及装置、系统、电器设备 |
| WO2021050691A1 (en) | 2019-09-10 | 2021-03-18 | Johnson Controls Technology Company | Model predictive maintenance system with short-term scheduling |
| CN111476400B (zh) * | 2020-03-11 | 2023-05-12 | 珠海格力电器股份有限公司 | 电路故障预测方法、装置、设备及计算机可读介质 |
-
2021
- 2021-11-25 DE DE102021130996.4A patent/DE102021130996A1/de active Pending
-
2022
- 2022-10-11 WO PCT/EP2022/078192 patent/WO2023094064A1/de not_active Ceased
- 2022-10-11 EP EP22800277.0A patent/EP4437285A1/de not_active Withdrawn
Also Published As
| Publication number | Publication date |
|---|---|
| DE102021130996A1 (de) | 2023-05-25 |
| WO2023094064A1 (de) | 2023-06-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| DE102015112594A1 (de) | System und Verfahren für den verbesserten Betrieb von Windparks | |
| WO2015075067A1 (de) | Verfahren und windenergieanlage zur blitzwarnung | |
| WO2023094064A1 (de) | Verfahren zur fehlerprädiktion in einer hvac-anlage | |
| WO2014044485A2 (de) | Verfahren zur diagnose von streckenkomponenten eines streckennetzes des schienenverkehrs | |
| DE602005002818T2 (de) | Verfahren zur Überwachung der Betriebsleistungen einer Industrieanlage | |
| EP3430257B1 (de) | Verfahren zur bestimmung der windgeschwindigkeit sowie anlage zur durchführung desselben | |
| DE102018107233A1 (de) | Verfahren zur automatischen Prozessüberwachung und Prozessdiagnose eines stückbasierten Prozesses (batch-Fertigung), insbesondere eines Spritzgießprozesses und eine den Prozess durchführende Maschine oder ein den Prozess durchführender Maschinenpark | |
| EP2701020A1 (de) | Überwachung einer ersten Ausrüstung einer technischen Anlage zur Herstellung eines Produkts | |
| EP3649033B1 (de) | Verfahren zur untersuchung eines funktionsverhaltens einer komponente einer technischen anlage, computerprogramm und computerlesbares speichermedium | |
| WO2010026025A1 (de) | Verfahren zum betreiben einer messstelle und messstelle | |
| EP2667023B1 (de) | Steuerung eines Windenergiesystems | |
| EP3679246B1 (de) | Verfahren zum überwachen des zustands mindestens eines während des betriebs einer windkraftanlage belasteten bauteils | |
| EP2947426B1 (de) | Verfahren zum betreiben einer messstelle | |
| EP2250716B1 (de) | Überwachungseinrichtung für den betrieb von schaltschrankgeräten | |
| EP2774242B1 (de) | Verfahren zum erzeugen eines eine pendelung in einem elektrischen energieversorgungsnetz angebenden signals | |
| EP3184965B1 (de) | Verfahren zum anpassen einer reichweitenprädiktion eines kraftfahrzeugs anhand von umgebungsbedingungen und kraftfahrzeug | |
| EP4086454A1 (de) | Verfahren zum betreiben einer windenergieanlage, windenergieanlage und windpark | |
| DE102017131241B4 (de) | Überwachungsverfahren für eine Windkraftanlage, zugehörige Überwachungsvorrichtung sowie Windkraftanlage mit Überwachungsvorrichtung | |
| DE102021210569B4 (de) | Verfahren zum Betreiben einer Windenergieanlage in einem Windpark und Windparkmanager | |
| EP2914935B1 (de) | Messvorrichtung, messanordnung und verfahren zur bestimmung einer messgrösse | |
| EP4348825A1 (de) | Verfahren und überwachungseinrichtung zur zustandsüberwachung einer maschine | |
| EP1916585B1 (de) | Verfahren und Vorrichtung zur Erzeugung temperaturabhängiger Kennlinien sowie deren Linearisierung | |
| DE102014109949B4 (de) | Computerimplementiertes Verfahren zur Beurteilung eines energieeffizienten Betriebs einer gebäudetechnischen Anlage | |
| DE112018001692T5 (de) | Informationsverarbeitungsvorrichtung, informationsverarbeitungsverfahren und programm | |
| DE102017131389A1 (de) | Verfahren zum Kalibrieren von Nominalfrequenzen |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: UNKNOWN |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE |
|
| PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE |
|
| 17P | Request for examination filed |
Effective date: 20240523 |
|
| AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC ME MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
| DAV | Request for validation of the european patent (deleted) | ||
| DAX | Request for extension of the european patent (deleted) | ||
| RAP1 | Party data changed (applicant data changed or rights of an application transferred) |
Owner name: VIESSMANN HOLDING INTERNATIONAL GMBH |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE APPLICATION IS DEEMED TO BE WITHDRAWN |
|
| 18D | Application deemed to be withdrawn |
Effective date: 20250103 |