BAS system-based electromechanical equipment fault prediction method and system

Abstract

The embodiment of the invention provides an electromechanical equipment fault prediction method and system based on a BAS system, and the method comprises the steps: firstly constructing an equipment state reference library based on a historical operation log of the BAS system, and then obtaining an equipment multi-source monitoring data set through a real-time monitoring network of the BAS system, and covering part sensor data, system control instruction data and environment feedback data. And then performing state alignment verification processing on the multi-source monitoring data set and the equipment state reference library to generate a state alignment verification result indicating a matching degree. And performing fault feature level derivation processing based on the result, and generating an equipment fault precursor feature chain containing an abnormal transmission path. And finally, an equipment fault dynamic risk assessment report is generated according to the evolution trend of the fault precursor feature chain and is synchronized to an operation and maintenance decision module of the BAS system, so that the probability of equipment fault occurrence is effectively reduced, the operation reliability and stability of electromechanical equipment are improved, and economic loss and safety risks caused by equipment faults are reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of rail transit environment and equipment monitoring system and electromechanical equipment maintenance technology, in particular to an electromechanical equipment fault prediction method and system based on a BAS system. BACKGROUND

[0002] In urban rail transit, the environment and equipment monitoring system (BAS system) plays a crucial role, which can centrally monitor, manage and control various types of electromechanical equipment to ensure efficient and stable operation of the facilities. As the core component of the environment and equipment monitoring system, the operation state of the electromechanical equipment directly affects the performance and safety of the entire system.

[0003] Currently, the main methods for handling faults of electromechanical equipment are post-maintenance and regular maintenance. Post-maintenance is to repair the equipment after it fails, which will cause the equipment downtime to be prolonged, affecting the normal operation of the facilities, increasing the maintenance cost and indirect losses caused by downtime. Regular maintenance is to check and maintain the equipment according to a predetermined time interval, however, the above maintenance methods lack pertinence and cannot be adjusted according to the actual operation state of the equipment, which may result in over-maintenance or insufficient maintenance. Over-maintenance will increase unnecessary costs and waste resources, while insufficient maintenance cannot timely discover potential problems of the equipment, which may lead to sudden failures.

[0004] Although the existing fault prediction technology can warn about equipment failures to some extent, it is mostly based on a single data source or simple parameter threshold judgment, without fully considering the complex correlation of the equipment under different operation modes and the synergistic effect between multi-source data, which is difficult to accurately and comprehensively predict equipment failures and cannot meet the high requirements of modern facilities for reliable operation of electromechanical equipment. SUMMARY

[0005] Therefore, the purpose of the present application is to provide an electromechanical equipment fault prediction method and system based on a BAS system.

[0006] In combination with the first aspect of the present application, an electromechanical equipment fault prediction method based on a BAS system is provided, which is applied to an electromechanical equipment fault prediction system based on a BAS system, and the method comprises:

[0007] constructing a device state benchmark library based on historical operation logs of the BAS system, wherein the device state benchmark library contains parameter correlation rules and component synergistic behavior patterns of the normal state of the equipment under different operation modes;

[0008] A multi-source monitoring data set of the equipment is obtained through a real-time monitoring network of the BAS system, and the multi-source monitoring data set includes component sensor data, system control instruction data, and environmental feedback data.

[0009] A state alignment verification process is performed on the multi-source monitoring data set and the equipment state reference library to generate a state alignment verification result, which is used to indicate the matching degree of the monitoring data and the reference library in the parameter dimension, time scale, and correlation.

[0010] Based on the state alignment verification result, a fault feature hierarchical derivation process is performed to generate an equipment fault precursor feature chain, which includes a progressive abnormality transmission path from parameter abnormality to component abnormality to system abnormality.

[0011] An equipment fault dynamic risk assessment report is generated according to the evolution trend of the fault precursor feature chain, and the equipment fault dynamic risk assessment report is synchronized to an operation and maintenance decision module of the BAS system.

[0012] In combination with the second aspect of the present application, a BAS system-based mechanical and electrical equipment fault prediction system is provided, which includes a machine-readable storage medium and a processor. The machine-readable storage medium stores machine-executable instructions. When the processor executes the machine-executable instructions, the BAS system-based mechanical and electrical equipment fault prediction system implements the aforementioned BAS system-based mechanical and electrical equipment fault prediction method.

[0013] In combination with the third aspect of the present application, a computer-readable storage medium is provided, which stores computer-executable instructions. When the computer-executable instructions are executed, the aforementioned BAS system-based mechanical and electrical equipment fault prediction method is implemented.

[0014] In combination with any of the above aspects, a device state reference library is constructed based on historical operation logs of the BAS system, which covers parameter correlation rules and component cooperative behavior patterns of the equipment in a normal state under different operation modes, and can fully consider the complexity and diversity of equipment operation. A multi-source monitoring data set of the equipment is obtained through a real-time monitoring network of the BAS system, which includes component sensor data, system control instruction data, and environmental feedback data, comprehensively reflects the operation state of the equipment from multiple dimensions, and improves the integrity and reliability of the data.

[0015] The state alignment verification result generated by the state alignment verification processing of the multi-source monitoring data set and the equipment state benchmark library can accurately indicate the matching degree of the monitoring data and the benchmark library in the parameter dimension, time scale and correlation. The equipment fault precursor feature chain generated by the fault feature level derivation processing based on the state alignment verification result clearly presents the progressive abnormal transmission path from parameter anomaly to component anomaly to system anomaly, which helps to deeply understand the generation and development process of the fault. According to the evolution trend of the equipment fault precursor feature chain, an equipment fault dynamic risk assessment report is generated, and the report is synchronized to the operation and maintenance decision module of the BAS system, realizing the organic combination of fault prediction and operation and maintenance decision, which can timely and accurately provide equipment fault risk information for operation and maintenance personnel, so that they can take targeted maintenance measures in advance, effectively reduce the probability of equipment failure, improve the operation reliability and stability of mechanical and electrical equipment, and reduce economic losses and safety risks caused by equipment failure. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained without creative labor.

[0017] Figure 1 The flowchart of the mechanical and electrical equipment fault prediction method based on the BAS system provided by the embodiments of the present application. DETAILED DESCRIPTION

[0018] In order to make the technical personnel in the art better understand the present application scheme, the following will combine the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of the present application.

[0019] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish different objects, not to describe a specific order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, device, product or end including a series of steps or units is not limited to the listed steps or units, but can optionally include steps or units not listed, or can optionally include other steps or units inherent to the process, method, product or end.

[0020] Reference to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase "in an embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are they necessarily mutually exclusive of one another. It is expressly understood that any of the embodiments described herein can be combined with any of the other embodiments unless specifically noted otherwise.

[0021] Figure 1 The flowchart of the BAS system-based mechanical and electrical equipment failure prediction method provided by the embodiments of the application is shown, and it should be understood that in other embodiments, the order of some steps of the BAS system-based mechanical and electrical equipment failure prediction method of the embodiments can be shared based on actual needs, or some steps can be omitted or maintained. The BAS system-based mechanical and electrical equipment failure prediction method includes the following steps in detail:

[0022] The embodiments provide a BAS system-based mechanical and electrical equipment failure prediction method, which is mainly applied to mechanical and electrical equipment in urban rail transit, such as a chiller of a central air conditioning system, to realize real-time monitoring and failure prediction of the chiller through a BAS system, so as to ensure stable operation of the equipment. The steps of the method will be described in detail below.

[0023] Step S110: Constructing a device state benchmark library based on historical operation logs of the BAS system, wherein the device state benchmark library contains parameter correlation rules and component cooperative behavior modes of the device in a normal state under different operation modes.

[0024] In the embodiments, the chiller of the central air conditioning system is taken as an object, and the BAS system records historical operation logs of the chiller under various operation conditions. First, operation data of the chiller in a failure-free time period is selected from the historical operation logs, and the data is used as a basis for constructing the device state benchmark library. Different operation modes include a start-up mode, a stable operation mode, and a shutdown mode of the chiller. For the start-up mode, the operation data can include current, voltage, start-up time of the compressor, and initial temperatures of components such as the condenser and the evaporator; the data in the stable operation mode includes working frequency of the compressor, condensing temperature, evaporating temperature, cooling water flow rate, and chilled water flow rate; and the data in the shutdown mode can involve time for which the compressor stops working and temperature drop rate of each component.

[0025] Step S111: Selecting a subset of operation data of the device in a failure-free time period from the historical operation logs of the BAS system, wherein the subset of operation data contains complete operation cycle data of the device in the start-up mode, the stable operation mode, and the shutdown mode.

[0026] In the screening process, it is necessary to determine the fault-free judgment criteria of the water chiller, for example, in a period of time, the BAS system has not recorded any fault alarm information about the water chiller, and all operating parameters are within the normal range specified by the equipment manufacturer. Then, the operating data in the time period that meets these criteria is extracted from the historical operation log to form a subset of operating data. For the start-up mode, the complete operating cycle refers to the time period from the start of the compressor to the stable operation state; the complete cycle of the stable operation mode refers to the time period during which the equipment works stably; the complete cycle of the shutdown mode refers to the time period from the start of the equipment to the complete stop of the operation. For example, the complete operating cycle of the start-up mode can be 5 minutes, and the current, voltage, temperature and other data within the 5 minutes will be included in the operating data subset.

[0027] Step S112: performing parameter association mining processing on the operating data subset, extracting the dependency relationship between different equipment parameters in the same operating mode, and generating parameter association rules, the parameter association rules including positive association threshold, reverse association threshold and independent association range between parameters.

[0028] For the screened operating data subset, taking the stable operation mode as an example, the dependency relationship between different parameters needs to be analyzed. For example, the condensation temperature and the cooling water flow, in the stable operation, usually the cooling water flow increases, and the condensation temperature decreases, and there is a positive association between the two. Through the analysis of a large amount of historical data, the positive association threshold between them can be determined, that is, when the cooling water flow changes within a certain range, the corresponding change range of the condensation temperature. Assuming that after analysis, when the cooling water flow changes between Q1 and Q2, the condensation temperature changes between T1 and T2, then the positive association threshold can be expressed as the corresponding temperature range within the flow range. Reverse association can exist between the working frequency of the compressor and the evaporation temperature, when the working frequency of the compressor increases, the evaporation temperature decreases, and the reverse association threshold between them can be determined through data mining. For some weakly associated parameters, such as the pressure of the condenser and the pressure of the evaporator, they can be in an independent association range in the stable operation mode, that is, the change of one parameter will not have a significant impact on the other parameter, and their respective independent change ranges are determined as the independent association range through analysis.

[0029] Step S113: analyzing the action timing relationship between components in the operating data subset, extracting component cooperative behavior mode, the component cooperative behavior mode including time delay range of component action, action sequence constraint and upper limit of cooperative action frequency.

[0030] The components of a water chiller include a compressor, a condenser fan, an expansion valve, a water pump, etc. In the start-up mode, there is a certain time sequence relationship between the actions of the components. For example, when starting up, the water pump is usually started first, then the expansion valve is opened, then the compressor is started, and finally the condenser fan is started. By analyzing the action time records in the operation data subset, the time delay range between the actions of the components can be determined, such as the expansion valve being opened within the time range from t1 to t2 after the water pump is started. The action sequence constraint clearly specifies the order of the actions of the components, and the order cannot be reversed, such as the water pump cannot be started after the compressor is started. The upper limit of the cooperative action frequency refers to the maximum number of cooperative actions of the related components within a unit of time, for example, the frequency of cooperative adjustment of the condenser fan and the water pump cannot exceed f times per hour in the stable operation mode, so as to avoid damage caused by excessive frequent actions of the components.

[0031] Step S114: standardize and encode the parameter association rules and the component cooperative behavior patterns, and store them in the device state reference library according to the operation modes. The storage structure of the device state reference library includes a mode identification field, a parameter association field, and a cooperative behavior field.

[0032] The standardization and encoding process converts the parameter association rules and the component cooperative behavior patterns into a unified data format, so as to facilitate the storage and query of the device state reference library. For example, for the positive association threshold in the parameter association rules, a specific character combination is used to represent the parameter name, the association type, and the threshold range, such as "condensing temperature-cooling water flow-positive association-T1-T2-Q1-Q2", where T1 and T2 are the range of the condensing temperature, and Q1 and Q2 are the range of the cooling water flow. For the component cooperative behavior pattern, the encoding can be "start-up mode-water pump-expansion valve-compressor-condenser fan-t1-t2-sequence constraint-f upper limit". The device state reference library is stored in categories according to the start-up mode, the stable operation mode, the shutdown mode, etc. Each mode corresponds to an entry containing a mode identification field, such as "start-up mode 001"; a parameter association field storing the encoding of all parameter association rules in this mode; and a cooperative behavior field storing the encoding of the component cooperative behavior pattern in this mode.

[0033] Step S120: obtain a set of device multi-source monitoring data through the real-time monitoring network of the BAS system, which includes component sensor data, system control instruction data, and environmental feedback data.

[0034] The real-time monitoring network of the BAS system covers all key parts of the water chiller and can collect a variety of data related to the operation of the device in real time. These data will be aggregated to form a set of multi-source monitoring data.

[0035] Step S121: Call the sensor management module of the BAS system to collect real-time running data of the key components of the equipment as component sensor data, which includes temperature sensor data, vibration sensor data and pressure sensor data.

[0036] The sensor management module is responsible for managing the sensors distributed on the key components of the water chiller. The temperature sensor data includes the suction temperature and discharge temperature of the compressor, the inlet water temperature and outlet water temperature of the condenser, the inlet water temperature and outlet water temperature of the evaporator, etc. These data are collected by temperature sensors installed at the corresponding positions in real time, for example, the temperature sensor at the suction port of the compressor collects data every 10 seconds. The vibration sensor data comes from vibration sensors installed on rotating components such as compressors and water pumps, which are used to monitor the vibration of these components during operation. The data includes information such as amplitude and frequency of vibration. The pressure sensor data includes the pressure of the condenser, the pressure of the evaporator, the suction pressure and discharge pressure of the compressor, etc., which are monitored by pressure sensors in real time.

[0037] Step S122: Access the control instruction log module of the BAS system to extract the current received control instruction sequence of the equipment as system control instruction data, which includes start instruction, speed regulation instruction and shutdown instruction.

[0038] The control instruction log module records all the control instructions sent by the BAS system to the water chiller. The start instruction is an instruction to control the water chiller to start running, which contains information such as start time, target parameters at start time, etc., for example, "2024-05-2008:00:00 start target condensing temperature 35℃". The speed regulation instruction is used to adjust the working frequency of the compressor, the rotating speed of the water pump and the fan, etc., such as "2024-05-2009:30:00 speed regulation compressor frequency increase 5Hz". The shutdown instruction is an instruction to control the water chiller to stop running, which contains information such as shutdown time and shutdown mode, etc., for example, "2024-05-2018:00:00 shutdown normal shutdown". When extracting the current received control instruction sequence, a time range needs to be determined, such as the control instructions in the past 1 hour, to form the system control instruction data.

[0039] Step S123: Obtain real-time feedback data of the BAS system environment monitoring subsystem as environment feedback data, which includes temperature and humidity data, air flow speed data and dust concentration data of the area where the equipment is located.

[0040] The environmental monitoring subsystem is deployed in the machine room where the water chiller is located. It collects temperature and relative humidity data in the machine room through temperature and humidity sensors, for example, the temperature is 25°C and the relative humidity is 60%. Airflow velocity data is monitored by airflow sensors to reflect the air flow in the machine room, such as airflow velocity of 0.5 meters per second. Dust concentration data is obtained through dust sensors to assess the air quality in the machine room, such as dust concentration of 0.1 milligrams per cubic meter. These environmental feedback data are transmitted to the BAS system in real time as part of the environmental feedback data.

[0041] Step S124: Time stamp synchronization processing is performed on the component sensor data, system control instruction data and environmental feedback data to generate a multi-source monitoring data set with consistent time sequence.

[0042] Due to the differences in the collection and generation time of component sensor data, system control instruction data and environmental feedback data, in order to ensure the accuracy of subsequent analysis, time stamp synchronization processing is needed. First, an accurate time stamp is added to each piece of data, and the accuracy of the time stamp can reach milliseconds. Then, taking a certain uniform time interval, for example, 1 second, as the basis, the data collected within the time interval is classified as data at the same time point. For multiple data of the same type within the same time interval, the average value or the last data can be taken. For example, within a 1-second time interval, the temperature sensor collects 3 data, 25°C, 25.1°C and 25.2°C, and the average value 25.1°C is taken as the temperature data at this time point. After the above processing, the multi-source monitoring data set generated has consistent time sequence of each data, which is convenient for subsequent state alignment verification and other processing.

[0043] Step S130: State alignment verification processing is performed on the multi-source monitoring data set and the device state reference library to generate a state alignment verification result, which is used to indicate the matching degree of the monitoring data and the reference library in the parameter dimension, time scale and correlation.

[0044] State alignment verification processing is to compare the multi-source monitoring data set obtained in real time with the data in the device state reference library under the corresponding running mode to determine the matching of the two in multiple aspects.

[0045] Step S131: Extract the current running mode identifier in the multi-source monitoring data set, and retrieve the corresponding parameter correlation rule and component cooperative behavior mode from the device state reference library as the target reference subset according to the running mode identifier.

[0046] The current operation mode information of the water chiller is contained in the multi-source monitoring data set. For example, by analyzing the start command in the system control command data or combining the change trend of the component sensor data, it can be determined that the current is in stable operation mode, and the corresponding operation mode identifier such as "stable operation mode 002" is extracted. Then, according to the identifier, the corresponding parameter correlation rule and component cooperative behavior mode in the stable operation mode are searched in the device state reference library, and these data are combined into the target reference subset.

[0047] Step S132: The parameter dimension of the multi-source monitoring data set is verified, the monitoring data contains all parameter types involved in the parameter correlation rule in the target reference subset, and the parameter dimension matching mark is generated.

[0048] The parameter correlation rule in the target reference subset involves multiple parameter types. For example, in the stable operation mode, it may involve the compressor operating frequency, condensing temperature, evaporating temperature, cooling water flow, chilled water flow, etc. The parameter dimension of the multi-source monitoring data set is verified, that is, whether all these parameter types of data are contained in the set. If all parameter types exist, the generated parameter dimension matching mark is "match"; if any parameter type is missing, the mark is "not match", and the missing parameter type is recorded. For example, if the multi-source monitoring data set is missing the parameter type of cooling water flow, the parameter dimension matching mark is "not match, missing cooling water flow".

[0049] Step S133: Calculate the time window length of the multi-source monitoring data set and the time deviation of the typical operation cycle in the target reference subset, generate the time scale matching degree value, and the time scale matching degree value is calculated by the absolute value of the difference between the time window length and the typical operation cycle.

[0050] Firstly, the time window length of the multi-source monitoring data set is determined, that is, the time span of the data covered by the set, for example, from 10:00:00 to 10:05:00, the time window length is 300 seconds. The typical operation cycle in the target reference subset refers to the standard time length of a complete operation process of the device under the corresponding operation mode, for example, the typical operation cycle in the stable operation mode is 1800 seconds. Then, the absolute value of the difference between the time window length and the typical operation cycle is calculated, that is, |300-1800|=1500 seconds, and the absolute value of the difference is the time scale matching degree value, which reflects the difference between the time span of the multi-source monitoring data set and the standard cycle.

[0051] Step S134: Analyze the actual correlation between parameters in the multi-source monitoring data set and the compliance of the parameter correlation rule in the target reference subset, generate a correlation matching rate, and the correlation matching rate is calculated by the overlapping ratio of the actual correlation and the rule correlation.

[0052] For each parameter correlation rule in the target reference subset, analyze whether the actual correlation between the corresponding parameters in the multi-source monitoring data set conforms to the rule. For example, a certain parameter correlation rule stipulates that in the stable operation mode, when the cooling water flow is between Q1 and Q2, the condensing temperature should be between T1 and T2. In the multi-source monitoring data set, the number of times when the condensing temperature is within the range of T1 to T2 when the cooling water flow is within the range of Q1 to Q2 is counted, and the total number of times when the cooling water flow is within the range is counted. The correlation matching rate is the ratio of the former to the latter. Assuming that in the multi-source monitoring data set, the total number of times when the cooling water flow is within the range of Q1 to Q2 is 100 times, and the number of times when the condensing temperature is within the range of T1 to T2 is 80 times, then the correlation matching rate of this rule is 0.8. For all parameter correlation rules in the target reference subset, the matching rate is calculated in the above manner, and then the average of these rates is taken as the total correlation matching rate.

[0053] Step S135: Integrate the parameter dimension matching mark, time scale matching degree value and correlation matching rate to generate a state alignment verification result.

[0054] The parameter dimension matching mark, time scale matching degree value and correlation matching rate are integrated in a certain format to form a state alignment verification result. For example, the state alignment verification result can be expressed as "parameter dimension matching mark: not matched, missing cooling water flow; time scale matching degree value: 1500 seconds; correlation matching rate: 0.75". The above result can clearly reflect the matching of the multi-source monitoring data set and the target reference subset in the parameter dimension, time scale and correlation.

[0055] Step S140: Based on the state alignment verification result, perform fault feature level derivation processing to generate a device fault precursor feature chain, and the fault precursor feature chain contains a progressive abnormal transmission path from parameter anomaly to component anomaly to system anomaly.

[0056] According to the various mismatching conditions reflected in the state alignment verification result, the possible fault features are gradually deduced, and the fault precursor feature chain is constructed according to the parameter anomaly, component anomaly and system anomaly level, so as to clarify the transmission path and development trend of the anomaly.

[0057] Step S141: When the parameter dimension matching flag in the state alignment verification result is marked as mismatching, locate the missing parameter type and mark it as a parameter-level abnormal point.

[0058] If the parameter dimension matching flag is marked as mismatching, it means that some parameter types in the target reference subset are missing in the multi-source monitoring data set, and these missing parameter types need to be located and marked.

[0059] Step S1411: Extract the parameter dimension matching flag in the state alignment verification result, and determine whether there is a missing parameter type.

[0060] The specific content of the parameter dimension matching flag obtained from the state alignment verification result is, for example, "mismatching, missing cooling water flow", from which it can be determined that there is a missing parameter type, i.e. cooling water flow.

[0061] Step S1412: If there is a missing parameter type, trace the sensor state of the missing parameter from the original collection record of the multi-source monitoring data set to determine sensor failure or data transmission interruption as the missing reason.

[0062] Check the original collection record of the multi-source monitoring data set to understand the collection of the cooling water flow parameter. If the original record shows that the sensor of this parameter has never returned data, or the returned data has always been invalid, it may be caused by sensor failure; if there was normal data returned before, but suddenly no data after a certain time point, and the collection of other parameters is normal, it may be caused by data transmission interruption, such as transmission line failure or data transmission module problem.

[0063] Step S1413: Generate a parameter missing type identifier according to the missing reason, the parameter missing type identifier including sensor failure type and data transmission interruption type.

[0064] If it is determined that the missing reason is sensor failure, the parameter missing type identifier can be "sensor failure-cooling water flow sensor"; if it is data transmission interruption, the identifier is "data transmission interruption-cooling water flow data transmission line".

[0065] Step S1414: Associate and record the missing parameter type, missing reason and parameter missing type identifier, generate a parameter-level abnormal point, and the parameter-level abnormal point includes a parameter name field, a missing reason field and a missing type field.

[0066] The cooling water flow (parameter name field), sensor failure (missing reason field), and "sensor failure-cooling water flow sensor" (missing type field) are associated and recorded to form a parameter-level abnormal point, such as "parameter name: cooling water flow; missing reason: sensor failure; missing type: sensor failure-cooling water flow sensor".

[0067] Step S142: When the time scale matching degree value in the state alignment verification result exceeds the preset deviation threshold, analyze the non-periodic fluctuation characteristics of the parameters in the monitoring data time window, and mark as a component-level abnormal point.

[0068] When the time scale matching degree value exceeds the preset deviation threshold, it indicates that there is a large difference between the time window of the multi-source monitoring data set and the typical operation cycle in the target reference subset, and the fluctuation of the parameters in the time window needs to be analyzed to determine whether there is a component-level abnormality.

[0069] Step S1421: Extract the time scale matching degree value in the state alignment verification result, and determine whether it exceeds the preset deviation threshold.

[0070] The preset deviation threshold is set according to the characteristics of the device and actual operation experience, for example, in a stable operation mode, the preset deviation threshold is 200 seconds. If the time scale matching degree value is 300 seconds, it exceeds the preset deviation threshold, and subsequent analysis is required.

[0071] Step S1422: If the preset deviation threshold is exceeded, perform fluctuation frequency analysis on the parameters in the time window of the multi-source monitoring data set, and calculate the fluctuation frequency of the parameters per unit time.

[0072] In this embodiment, the time window is 300 seconds, and the compressor operating frequency, condensing temperature, and evaporating temperature are selected for fluctuation frequency analysis. For the compressor operating frequency, the number of times its value changes in these 300 seconds is recorded, and assuming that it changes 15 times, the fluctuation frequency per unit time (1 second) is 15 divided by 300, resulting in 0.05 times per second. Similarly, the condensing temperature and evaporating temperature are also calculated in a similar manner, and their fluctuation frequencies are obtained, for example, the fluctuation frequency of the condensing temperature is 0.03 times per second, and the fluctuation frequency of the evaporating temperature is 0.04 times per second.

[0073] Step S1423: Identify the periodic characteristics of parameter fluctuations and generate periodic fluctuation identifiers and non-periodic fluctuation identifiers.

[0074] By analyzing the fluctuation of each parameter in the time window, it is determined whether it has periodicity. For example, the compressor operating frequency may fluctuate regularly according to a certain period in the normal stable operation mode, such as adjusting the frequency every 30 seconds. In the above case, a periodic fluctuation identifier is generated, such as "compressor operating frequency-periodic fluctuation". If the condensing temperature fluctuation does not show a clear regularity, it may rise rapidly at times and fall slowly at times, without a fixed period, then a non-periodic fluctuation identifier is generated, such as "condensing temperature-non-periodic fluctuation".

[0075] Step S1424: Perform amplitude analysis on the non-periodic fluctuation parameter, and calculate the difference between the fluctuation amplitude and the reference amplitude as the abnormal amplitude value.

[0076] For parameters marked as non-periodic fluctuation, such as condensing temperature, the fluctuation amplitude needs to be determined. First, find the maximum and minimum values of the parameter in the time window, and the difference between the two is the fluctuation amplitude. Assuming that the maximum value of the condensing temperature in the time window is 40℃, and the minimum value is 30℃, then the fluctuation amplitude is 10℃. The reference amplitude is the fluctuation amplitude of the parameter in the normal stable operation mode obtained from the target reference subset of the device state reference library, for example, the reference amplitude is 5℃. Then the abnormal amplitude value is 10℃ minus 5℃, which is 5℃.

[0077] Step S1425: Record the parameter name, fluctuation times and abnormal amplitude value of the non-periodic fluctuation, and generate a component-level abnormal point, which contains a parameter name field, a fluctuation times field and an abnormal amplitude field.

[0078] Record the condensing temperature (parameter name field), 0.03 times per second (fluctuation times field), and 5℃ (abnormal amplitude field) to form a component-level abnormal point, such as "parameter name: condensing temperature; fluctuation times: 0.03 times per second; abnormal amplitude: 5℃". This indicates that the component where the condensing temperature parameter is located may have an abnormality, because its fluctuation is non-periodic and the abnormal amplitude is large.

[0079] Step S143: When the matching rate of the association relationship in the state alignment verification result is lower than the preset matching threshold, identify the transmission direction and influence range of the abnormal association between parameters, and mark it as a system-level abnormal point.

[0080] If the matching rate of the association relationship is lower than the preset matching threshold, it means that there is a large difference between the actual association relationship between parameters in the multi-source monitoring data set and the parameter association rule in the target reference subset, which needs to be further analyzed to determine the system-level abnormal point.

[0081] Step S1431: Extract the matching rate of the association relationship in the state alignment verification result, and determine whether it is lower than the preset matching threshold.

[0082] The preset matching threshold is set according to the association relationship when the device is normally running. For example, the preset matching threshold is 0.8 in the stable running mode. If the association relationship matching rate in the state alignment verification result is 0.75, which is lower than the preset threshold, subsequent analysis and processing are required.

[0083] Step S1432: If the preset matching threshold is lower, the actual association relationship between the parameters in the multi-source monitoring data set is processed by graph model construction, and a parameter association graph is generated. The nodes of the parameter association graph represent the parameter types, and the edges represent the association strength between the parameters.

[0084] The compressor operating frequency, condensing temperature, cooling water flow, evaporating temperature, chilled water flow and other parameters are selected as nodes, and the actual association relationship between them is analyzed. For example, the change of the compressor operating frequency will affect the condensing temperature and the evaporating temperature, the change of the cooling water flow will affect the condensing temperature, and the change of the chilled water flow will affect the evaporating temperature. The thickness of the edge represents the association strength, and the stronger the association, the thicker the edge. Assuming that the association strength between the compressor operating frequency and the condensing temperature is 0.8, the association strength between the compressor operating frequency and the evaporating temperature is 0.7, the association strength between the cooling water flow and the condensing temperature is 0.6, and the association strength between the chilled water flow and the evaporating temperature is 0.5, these relationships are represented by a graph model to generate a parameter association graph.

[0085] Step S1433: Extract the standard parameter association graph from the target reference subset of the device state reference library, which contains the standard association strength between parameters.

[0086] The standard parameter association graph in the stable running mode is obtained from the target reference subset. The nodes in the graph are also the compressor operating frequency, condensing temperature, cooling water flow, evaporating temperature, chilled water flow and other parameters, and the thickness of the edge represents the standard association strength. For example, the standard association strength between the compressor operating frequency and the condensing temperature in the standard association graph is 0.9, the standard association strength between the compressor operating frequency and the evaporating temperature is 0.8, the standard association strength between the cooling water flow and the condensing temperature is 0.7, and the standard association strength between the chilled water flow and the evaporating temperature is 0.6.

[0087] Step S1434: Calculate the edge difference set of the parameter association graph and the standard parameter association graph, which contains the edges with enhanced association strength and the edges with weakened association strength.

[0088] The association strength of the corresponding edges in the parameter association graph and the standard parameter association graph is compared one by one. For the edge between the compressor operating frequency and the condensing temperature, the association strength in the parameter association graph is 0.8, and the association strength in the standard association graph is 0.9, the difference is -0.1, which is an edge with weakened association strength; for the edge between the compressor operating frequency and the evaporating temperature, the association strength in the parameter association graph is 0.7, and the association strength in the standard association graph is 0.8, the difference is -0.1, which is also an edge with weakened association strength; for the edge between the cooling water flow and the condensing temperature, the association strength in the parameter association graph is 0.6, and the association strength in the standard association graph is 0.7, the difference is -0.1, which is also an edge with weakened association strength; for the edge between the chilled water flow and the evaporating temperature, the association strength in the parameter association graph is 0.5, and the association strength in the standard association graph is 0.6, the difference is -0.1, which is an edge with weakened association strength. Collect these edges with changed association strength to form an edge difference set, for example, "edges with weakened association strength: compressor operating frequency-condensing temperature, compressor operating frequency-evaporating temperature, cooling water flow-condensing temperature, chilled water flow-evaporating temperature".

[0089] Step S1435: Analyze the transmission path of the association strength change in the edge difference set to determine the starting parameter of the abnormal association and the affected parameter range.

[0090] From the edge difference set, it can be seen that the association strength of multiple edges has been weakened. Further analysis of the relationship between these edges shows that the compressor operating frequency is a central parameter associated with multiple parameters, and the association strength between the compressor operating frequency and the condensing temperature and the evaporating temperature is weakened, which may be the starting point of abnormal association. The affected parameter range includes the condensing temperature, the evaporating temperature, the cooling water flow, and the chilled water flow, because these parameters are associated with the compressor operating frequency or other affected parameters. For example, because the association strength between the compressor operating frequency and the condensing temperature is weakened, the adjustment effect of the cooling water flow on the condensing temperature may also be affected, thereby affecting the parameter association of the entire system.

[0091] Step S1436: Record the starting parameter of the abnormal association, the transmission path, and the affected parameter range to generate a system-level abnormal point, which includes a starting parameter field, a transmission path field, and an impact range field.

[0092] The compressor operating frequency (initial parameter field), "compressor operating frequency → condensing temperature; compressor operating frequency → evaporating temperature; cooling water flow rate → condensing temperature; chilled water flow rate → evaporating temperature" (transmission path field), "condensing temperature, evaporating temperature, cooling water flow rate, chilled water flow rate" (influence range field) are associated and recorded to generate a system-level abnormal point, for example, "initial parameter: compressor operating frequency; transmission path: compressor operating frequency → condensing temperature; compressor operating frequency → evaporating temperature; cooling water flow rate → condensing temperature; chilled water flow rate → evaporating temperature; influence range: condensing temperature, evaporating temperature, cooling water flow rate, chilled water flow rate".

[0093] Step S144: Time sequence correlation analysis is performed on the parameter-level abnormal point, component-level abnormal point and system-level abnormal point to determine the time sequence and influence strength of the abnormality transmission from the parameter level to the component level and then to the system level.

[0094] The occurrence times of the parameter-level abnormal point, component-level abnormal point and system-level abnormal point are collected for time sequence correlation analysis. For example, the parameter-level abnormal point (missing cooling water flow rate) occurs at 10:00:00, the component-level abnormal point (non-periodic fluctuation of condensing temperature) occurs at 10:02:00, and the system-level abnormal point (compressor operating frequency correlation abnormality) occurs at 10:05:00. Thus, it can be determined that the time sequence of abnormality transmission is that the parameter-level abnormality occurs first, then the component-level abnormality, and finally the system-level abnormality. At the same time, the influence strength between the abnormal points is analyzed. The influence strength of the parameter-level abnormality on the component-level abnormality can be measured by the correlation degree between them, for example, set to 0.6; the influence strength of the component-level abnormality on the system-level abnormality is set to 0.7. These influence strengths are obtained according to the analysis of similar abnormality transmission in historical data.

[0095] Step S145: A fault precursor feature chain is constructed based on the time sequence and influence strength, and the fault precursor feature chain includes abnormal point type, abnormality transmission time interval and abnormality influence strength parameters.

[0096] According to the time sequence and influence strength, a fault precursor feature chain is constructed. The abnormal point types are in turn the parameter-level abnormal point, component-level abnormal point and system-level abnormal point. The abnormality transmission time interval refers to the time difference between the occurrence of the previous abnormal point and the occurrence of the next abnormal point. The time interval between the parameter-level abnormal point and the component-level abnormal point is 2 minutes, and the time interval between the component-level abnormal point and the system-level abnormal point is 3 minutes. The abnormality influence strength parameters are 0.6 and 0.7 determined in step S144. Therefore, the fault precursor feature chain can be represented as "parameter-level abnormal point → (time interval 2 minutes, influence strength 0.6) → component-level abnormal point → (time interval 3 minutes, influence strength 0.7) → system-level abnormal point".

[0097] Step S150: generating a device failure dynamic risk assessment report according to the evolution trend of the failure precursor feature chain, and synchronizing the device failure dynamic risk assessment report to an operation and maintenance decision module of the BAS system.

[0098] By analyzing the evolution trend of the failure precursor feature chain, the risk of device failure is evaluated, and a corresponding report is generated, which is timely delivered to the operation and maintenance decision module for taking corresponding measures.

[0099] Step S151: extracting abnormal transmission time interval and abnormal influence intensity parameters in the failure precursor feature chain.

[0100] The abnormal transmission time interval is extracted from the failure precursor feature chain, that is, 2 minutes from the parameter level abnormal point to the component level abnormal point, and 3 minutes from the component level abnormal point to the system level abnormal point; the abnormal influence intensity parameters are 0.6 and 0.7.

[0101] Step S152: based on the abnormal transmission time interval, predicting the length of time required for the abnormality to be transmitted from the current level to the next level, and generating an abnormal transmission time prediction value.

[0102] According to the evolution of similar failure precursor feature chains in historical data, combined with the current abnormal transmission time interval, the length of time required for the abnormality to be transmitted from the system level abnormal point to the next level (i.e. device failure) is predicted. It is assumed that through analysis, the abnormal transmission time prediction value under the current condition is 5 minutes.

[0103] Step S153: based on the abnormal influence intensity parameter, calculating the influence degree of the abnormality on the device function, and generating a function influence degree value.

[0104] The abnormal influence intensity parameters are calculated comprehensively, for example, using a weighted average method, giving the same weight to 0.6 and 0.7, and calculating (0.6+0.7)÷2=0.65, which is the function influence degree value, reflecting the influence degree of the abnormality on the chiller function.

[0105] Step S154: combining the abnormal transmission time prediction value and the function influence degree value, constructing a failure risk assessment model, the failure risk assessment model including a risk level calculation function and a risk evolution curve.

[0106] By processing the abnormal transmission time prediction value and the function influence degree value, a model capable of evaluating the risk of device failure is constructed.

[0107] For example, step S1541: normalizing the abnormal transmission time prediction value to generate a time risk factor in the range of 0 to 1.

[0108] The abnormal delivery time prediction value is 5 minutes, the longest possible delivery time is set to 10 minutes, and the shortest is 0 minutes. The normalization method is (longest time - abnormal delivery time prediction value) ÷ (longest time - shortest time), that is, (10-5) ÷ (10-0) = 0.5, and the time risk factor is 0.5.

[0109] Step S1542: The function impact degree value is normalized to generate a function risk factor in the range of 0 to 1.

[0110] The function impact degree value is 0.65, which is already in the range of 0 to 1, so it can be directly used as the function risk factor, that is, 0.65.

[0111] Step S1543: The time risk factor and the function risk factor are weighted and summed to generate a comprehensive risk index, and the weight coefficient of the weighted sum processing is dynamically adjusted according to the device type.

[0112] For the important equipment on the water chiller, the weight coefficient of the time risk factor is set to 0.6, and the weight coefficient of the function risk factor is set to 0.4. The comprehensive risk index = time risk factor × 0.6 + function risk factor × 0.4 = 0.5 × 0.6 + 0.65 × 0.4 = 0.3 + 0.26 = 0.56.

[0113] Step S1544: According to the numerical range of the comprehensive risk index, the risk level is divided into low risk level, medium risk level and high risk level.

[0114] The comprehensive risk index is set to be in the low risk level range of 0 to 0.3, in the medium risk level range of 0.3 to 0.7, and in the high risk level range of 0.7 to 1. Since the current comprehensive risk index is 0.56, it belongs to the medium risk level.

[0115] Step S1545: Based on the historical evolution data of the fault precursor feature chain, a trend curve of risk change over time is fitted to generate a risk evolution curve, and the risk evolution curve includes a risk index change rate parameter over time.

[0116] The historical evolution data of the similar fault precursor feature chain in the past is collected, which includes the comprehensive risk index at different time points. For example, in a similar situation in the past, the comprehensive risk index at time point t1 is 0.3, at t2 is 0.4, at t3 is 0.5, and at t4 is 0.6. According to these data, a trend curve of risk change over time is fitted, which shows an upward trend. By calculating the ratio of the risk index difference and the time difference of adjacent time points, the risk index change rate parameter over time is obtained, for example, the change rate parameter is calculated to be 0.02 per minute.

[0117] Step S1546: combine the risk level division rule and the risk evolution curve to generate a failure risk assessment model containing a risk level calculation function and a risk evolution curve.

[0118] The risk level division rule (i.e., the correspondence between the comprehensive risk index and the risk level) and the risk evolution curve (containing a change rate parameter of 0.02 per minute) are combined to form a failure risk assessment model. The model can calculate the comprehensive risk index according to the input abnormal transmission time prediction value and function impact degree value, determine the risk level, and predict the future risk change through the risk evolution curve.

[0119] Step S155: calculate the current failure risk level of the equipment and the risk evolution trend in the future time period through the failure risk assessment model to generate an equipment failure dynamic risk assessment report.

[0120] The abnormal transmission time prediction value of 5 minutes and the function impact degree value of 0.65 are input into the failure risk assessment model, and the current failure risk level is calculated to be the medium risk level. According to the risk evolution curve and the change rate parameter of 0.02 per minute, the risk evolution trend in the future 10 minutes is predicted, for example, the comprehensive risk index will reach 0.66 after 5 minutes and 0.76 after 10 minutes, entering the high risk level. These information is arranged into an equipment failure dynamic risk assessment report, which includes the current risk level, abnormal transmission time prediction value, function impact degree value, risk evolution trend prediction, etc.

[0121] Step S156: call the interface protocol of the BAS system to transmit the equipment failure dynamic risk assessment report to the storage unit and display unit of the operation and maintenance decision module.

[0122] Through the interface protocol of the BAS system, such as the BACnet protocol, the equipment failure dynamic risk assessment report is sent to the operation and maintenance decision module. The storage unit of the operation and maintenance decision module stores the report for subsequent query and analysis; the display unit displays the main content of the report, such as the current risk level and future risk trend, to the operation and maintenance personnel, so that they can understand the failure risk situation of the equipment in time and take appropriate maintenance measures.

[0123] In the above embodiment, the BAS system-based mechanical and electrical equipment failure prediction system for executing the above method embodiment has at least one processor, a control module (chipset) coupled to at least one of the processor(s), a memory coupled to the control module, a non-volatile memory (NVM) / storage device coupled to the control module, at least one loading / output device coupled to the control module, and a network interface coupled to the control module.

[0124] The processor(s) can include at least one single-core or multi-core processor, and the processor(s) can include any combination of general-purpose processors or special-purpose processors (e.g., graphics processors, application processors, baseband processors, etc.). For some alternative implementations, the BAS system-based mechanical and electrical equipment failure prediction system can be implemented as an electronic device, such as a gateway, described in embodiments of the present application.

[0125] For some alternative implementations, the BAS system-based mechanical and electrical equipment failure prediction system can include at least one computer-readable medium (e.g., memory or NVM / storage device) with instructions and at least one processor integrated with the at least one computer-readable medium configured to execute the instructions to implement modules to perform the acts described in the present disclosure.

[0126] For one embodiment, the control module can include any suitable interface controller to provide any suitable interface to at least one of the processor(s) and / or any suitable device or component in communication with the control module.

[0127] The control module can include a memory controller module to provide an interface to memory. The memory controller module can be a hardware module, a software module, and / or a firmware module.

[0128] Memory can be used, for example, to load and store data and / or instructions for the BAS system-based mechanical and electrical equipment failure prediction system. For one embodiment, the memory can include any suitable volatile memory, such as suitable DRAM.

[0129] For one embodiment, the control module can include at least one load / output controller to provide an interface to the NVM / storage device and the load / output device(s).

[0130] The NVM / storage device can be used, for example, to store data and / or instructions. The NVM / storage device can include any suitable non-volatile memory (e.g., flash memory) and / or can include any suitable non-volatile storage device(s) (e.g., at least one hard disk drive (HDD), at least one compact disk (CD) drive, and / or at least one digital versatile disk (DVD) drive).

[0131] The NVM / storage device can include a storage resource that is physically part of a device on which the BAS system-based mechanical and electrical equipment failure prediction system is installed, or it can be accessed by the device without being necessarily part of the device. For example, the NVM / storage device can be accessed over a network via the load / output device(s).

[0132] The at least one load / output device can provide an interface for the BAS system based mechanical and electrical equipment failure prediction system to communicate with any other suitable device, and can include a communication component, a pinyin component, a sensor component, etc. The network interface can provide an interface for the BAS system based mechanical and electrical equipment failure prediction system to communicate based on at least one network, and the BAS system based mechanical and electrical equipment failure prediction system can wirelessly communicate with at least one component of a wireless network based on at least one wireless network priori and / or any priori in a protocol, such as accessing a wireless network based on a communication priori.

[0133] For one embodiment, at least one of the at least one processor can be loaded with logic of at least one controller of the control module, such as a memory controller module. For one embodiment, at least one of the at least one processor can be loaded with logic of at least one controller of the control module to form a system on a chip (SoC). For one embodiment, at least one of the at least one processor can be fused on the same die as logic of at least one controller of the control module. For one embodiment, at least one of the at least one processor can be fused on the same die as logic of at least one controller of the control module to form a system on a chip (SoC).

[0134] The above describes the embodiments of the present application in detail, and the principles and implementation manners of the present application are described by applying specific examples; the above embodiment descriptions are only used to help understand the method of the present application and its core idea; meanwhile, based on the idea of the present application, the specific implementation manners and application ranges will be changed by the general technical personnel in the field, and the above description of the present application should not be understood as a limitation.

[0135] The embodiment of the present application discloses a computer readable storage medium storing a computer program for electronic data exchange, wherein the computer program causes a computer to execute the steps in the BAS system based mechanical and electrical equipment failure prediction method described in the foregoing embodiments.

[0136] The embodiment of the present application discloses a computer program product, which comprises a non-transitory computer readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute the steps in the BAS system based mechanical and electrical equipment failure prediction method described in the foregoing embodiments.

[0137] The device embodiments described above are only illustrative, wherein the modules described as separate components can or can not be physically separated, and the components displayed as modules can or can not be physical modules, i.e., can be located in one place or distributed to multiple modules. Part or all of the modules can be selected to achieve the purposes of the embodiments according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0138] Finally, it should be noted that: the above disclosed is only the preferred embodiment of the present application, only for the purpose of describing the technical solutions of the present application, not for its limitations; although the present application is described in detail with reference to the foregoing embodiments, those skilled in the art should understand; the technical solutions recorded in the foregoing embodiments can be modified, or some technical features can be replaced; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for predicting faults in electromechanical equipment based on a BAS system, characterized in that, The method includes: A device status benchmark library is constructed based on the historical operation logs of the BAS system. The device status benchmark library contains parameter association rules for the normal state of the device under different operating modes and component collaborative behavior patterns. The BAS system acquires a multi-source monitoring data set of the equipment through its real-time monitoring network. The multi-source monitoring data set includes component sensor data, system control command data, and environmental feedback data. The multi-source monitoring data set and the equipment status benchmark library are subjected to status alignment verification processing to generate a status alignment verification result. The status alignment verification result is used to indicate the degree of matching between the monitoring data and the benchmark library in terms of parameter dimensions, time scale and correlation. Based on the state alignment verification results, fault feature hierarchy derivation processing is performed to generate a device fault precursor feature chain. The fault precursor feature chain contains a progressive fault propagation path from parameter anomaly to component anomaly and then to system anomaly. A dynamic risk assessment report for equipment failure is generated based on the evolution trend of the fault precursor feature chain, and the dynamic risk assessment report for equipment failure is synchronized to the operation and maintenance decision module of the BAS system.

2. The method for predicting electromechanical equipment faults based on a BAS system according to claim 1, characterized in that, The device status baseline library built based on the historical operation logs of the BAS system includes: Filter the operation data subset of the equipment during the fault-free period from the historical operation log of the BAS system. The operation data subset includes complete operation cycle data of the equipment in start-up mode, stable operation mode and shutdown mode. The subset of operational data is subjected to parameter association mining processing to extract the dependency relationships between parameters of different devices under the same operational mode and generate parameter association rules. The parameter association rules include the positive association threshold, the negative association threshold, and the independent association range between parameters. Analyze the timing relationship of actions between components in the runtime data subset, and extract the component collaborative behavior pattern. The component collaborative behavior pattern includes the time delay range of component actions, action sequence constraints, and upper limit of collaborative action frequency. The parameter association rules and component collaborative behavior patterns are standardized and encoded, and stored in the device status benchmark library according to the operation mode. The storage structure of the device status benchmark library includes a mode identifier field, a parameter association field, and a collaborative behavior field.

3. The method for predicting electromechanical equipment faults based on a BAS system according to claim 1, characterized in that, The acquisition of multi-source monitoring data sets of equipment through the real-time monitoring network of the BAS system includes: The sensor management module of the BAS system is invoked to collect real-time operating data of key components of the equipment as component sensor data. The component sensor data includes temperature sensing data, vibration sensing data and pressure sensing data. Access the control command log module of the BAS system, extract the sequence of control commands currently received by the device as system control command data, which includes start command, speed adjustment command and stop command; The real-time feedback data of the BAS system's environmental monitoring subsystem is obtained as environmental feedback data, which includes temperature and humidity data, airflow velocity data, and dust concentration data of the area where the equipment is located. The sensor data, system control command data, and environmental feedback data of the aforementioned components are time-stamped and synchronized to generate a multi-source monitoring data set with time series consistency.

4. The method for predicting electromechanical equipment faults based on a BAS system according to claim 1, characterized in that, The step of performing state alignment verification processing on the multi-source monitoring data set and the equipment state benchmark library to generate state alignment verification results includes: Extract the current operating mode identifier from the multi-source monitoring data set, and retrieve the corresponding parameter association rules and component collaborative behavior patterns from the equipment status benchmark library based on the operating mode identifier as the target benchmark subset; The parameter dimensions of the multi-source monitoring data set are verified to include all parameter types involved in the parameter association rules in the target benchmark subset, and parameter dimension matching tags are generated. Calculate the time window length of the multi-source monitoring data set and the time deviation between the time window length and the typical operating cycle in the target reference subset, and generate a time scale matching degree value. The time scale matching degree value is calculated by the absolute value of the difference between the time window length and the typical operating cycle. The degree of conformity between the actual correlation between parameters in the multi-source monitoring data set and the correlation rules of parameters in the target benchmark subset is analyzed to generate a correlation matching rate. The correlation matching rate is calculated by the overlap ratio between the actual correlation and the rule correlation. The parameter dimension matching marker, time scale matching degree value, and association relationship matching rate are integrated and processed to generate a state alignment verification result.

5. The method for predicting electromechanical equipment faults based on a BAS system according to claim 1, characterized in that, The step of performing fault feature hierarchy derivation processing based on the state alignment verification results to generate a device fault precursor feature chain includes: When the parameter dimension matching is marked as mismatch in the state alignment verification result, the missing parameter type is located and marked as a parameter-level outlier. When the time scale matching degree value in the state alignment verification result exceeds the preset deviation threshold, the non-periodic fluctuation characteristics of the parameters within the monitoring data time window are analyzed and marked as component-level anomalies. When the correlation matching rate in the state alignment verification result is lower than the preset matching threshold, the transmission direction and influence range of abnormal correlation between parameters are identified and marked as system-level anomalies. Time-series correlation analysis is performed on the parameter-level anomalies, component-level anomalies, and system-level anomalies to determine the time sequence and impact intensity of anomalies propagating from the parameter level to the component level and then to the system level. Based on the time sequence and the intensity of influence, a fault precursor feature chain is constructed. The fault precursor feature chain includes parameters such as the anomaly type, the anomaly propagation time interval, and the anomaly influence intensity.

6. The method for predicting electromechanical equipment faults based on a BAS system according to claim 5, characterized in that, When the parameter dimension matching in the state alignment verification result is marked as mismatched, the missing parameter type is located and marked as a parameter-level outlier, including: Extract parameter dimension matching markers from the state alignment verification results to determine if there are any missing parameter types; If there is a missing parameter type, trace the sensor status of the missing parameter from the original acquisition records of the multi-source monitoring data set to determine the sensor failure or data transmission interruption as the cause of the missing parameter. A parameter missing type identifier is generated based on the cause of the missing information. The parameter missing type identifier includes sensor fault type and data transmission interruption type. The missing parameter type, missing reason, and missing parameter type identifier are associated and recorded to generate a parameter-level anomaly. The parameter-level anomaly includes a parameter name field, a missing reason field, and a missing type field.

7. The method for predicting electromechanical equipment faults based on a BAS system according to claim 5, characterized in that, When the time-scale matching degree value in the state alignment verification result exceeds a preset deviation threshold, the non-periodic fluctuation characteristics of the parameters within the monitoring data time window are analyzed and marked as component-level anomalies, including: Extract the time-scale matching degree value from the state alignment verification result and determine whether it exceeds a preset deviation threshold. If the preset deviation threshold is exceeded, the parameters within the time window of the multi-source monitoring data set are subjected to fluctuation frequency analysis processing to calculate the number of fluctuations of the parameters per unit time. Identify the periodic characteristics of parameter fluctuations and generate periodic fluctuation identifiers and non-periodic fluctuation identifiers; Amplitude analysis is performed on the parameters of non-periodic fluctuations, and the difference between the fluctuation amplitude and the benchmark amplitude is calculated as the abnormal amplitude. The parameter name, number of fluctuations, and abnormal amplitude of non-periodic fluctuations are associated and recorded to generate component-level anomaly points. The component-level anomaly points include parameter name field, number of fluctuations field, and abnormal amplitude field.

8. The method for predicting electromechanical equipment faults based on a BAS system according to claim 5, characterized in that, When the correlation matching rate in the state alignment verification result is lower than a preset matching threshold, the transmission direction and impact range of abnormal correlations between parameters are identified and marked as system-level anomalies, including: Extract the correlation matching rate from the state alignment verification results and determine whether it is lower than a preset matching threshold; If the value is below a preset matching threshold, a graph model is constructed to analyze the actual correlation between parameters in the multi-source monitoring data set, generating a parameter correlation graph. The nodes in the parameter correlation graph represent parameter types, and the edges represent the correlation strength between parameters. A standard parameter correlation graph is extracted from the target reference subset of the equipment status reference library, and the standard parameter correlation graph contains the standard correlation strength between parameters. Calculate the set of edge differences between the parameter association graph and the standard parameter association graph, wherein the set of edge differences includes edges with increased association strength and edges with decreased association strength; Analyze the propagation path of the change in association strength in the edge difference set to determine the starting parameters and the range of affected parameters of abnormal associations; The system-level anomaly point is generated by associating and recording the starting parameters, transmission path, and affected parameter range associated with the anomaly. The system-level anomaly point includes the starting parameter field, transmission path field, and affected range field.

9. The method for predicting electromechanical equipment faults based on a BAS system according to claim 1, characterized in that, The step of generating a dynamic risk assessment report for equipment failure based on the evolution trend of the failure precursor feature chain, and synchronizing the dynamic risk assessment report for equipment failure to the operation and maintenance decision module of the BAS system, includes: Extract the anomaly propagation time interval and anomaly influence intensity parameters from the fault precursor feature chain; Based on the anomaly propagation time interval, predict the time required for an anomaly to propagate from the current level to the next level, and generate an anomaly propagation time prediction value. Based on the aforementioned anomaly impact intensity parameter, the degree of impact of the anomaly on the equipment function is calculated, and a functional impact degree value is generated; By combining the predicted value of the anomaly transmission time and the value of the functional impact, a fault risk assessment model is constructed. The fault risk assessment model includes a risk level calculation function and a risk evolution curve. The fault risk assessment model is used to calculate the current fault risk level of the equipment and the risk evolution trend in the future time period, and to generate a dynamic fault risk assessment report of the equipment. The BAS system's interface protocol is invoked to transmit the device fault dynamic risk assessment report to the storage and display units of the operation and maintenance decision module.

10. A fault prediction system for electromechanical equipment based on a BAS system, characterized in that, The system includes a processor and a computer-readable storage medium storing machine-executable instructions, which, when executed by a computer, implement the electromechanical equipment fault prediction method based on any one of claims 1-9.

Images