CN118693312A - Fault diagnosis method and system for fuel cell standby power system - Google Patents
Fault diagnosis method and system for fuel cell standby power system Download PDFInfo
- Publication number
- CN118693312A CN118693312A CN202411162089.1A CN202411162089A CN118693312A CN 118693312 A CN118693312 A CN 118693312A CN 202411162089 A CN202411162089 A CN 202411162089A CN 118693312 A CN118693312 A CN 118693312A
- Authority
- CN
- China
- Prior art keywords
- representing
- fuel cell
- operation data
- state
- power system
- 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.)
- Pending
Links
- 239000000446 fuel Substances 0.000 title claims abstract description 79
- 238000000034 method Methods 0.000 title claims abstract description 60
- 238000003745 diagnosis Methods 0.000 title claims abstract description 59
- 239000011159 matrix material Substances 0.000 claims description 53
- UFHFLCQGNIYNRP-UHFFFAOYSA-N Hydrogen Chemical compound [H][H] UFHFLCQGNIYNRP-UHFFFAOYSA-N 0.000 claims description 22
- 230000008859 change Effects 0.000 claims description 22
- 239000001257 hydrogen Substances 0.000 claims description 22
- 229910052739 hydrogen Inorganic materials 0.000 claims description 22
- 230000007704 transition Effects 0.000 claims description 20
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 claims description 16
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 16
- 239000001301 oxygen Substances 0.000 claims description 16
- 229910052760 oxygen Inorganic materials 0.000 claims description 16
- 230000006870 function Effects 0.000 claims description 10
- 229910052757 nitrogen Inorganic materials 0.000 claims description 10
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 7
- 238000005259 measurement Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 2
- 238000001514 detection method Methods 0.000 abstract description 5
- 210000004027 cell Anatomy 0.000 description 59
- 230000006399 behavior Effects 0.000 description 14
- 230000008569 process Effects 0.000 description 13
- 230000004044 response Effects 0.000 description 7
- 238000006243 chemical reaction Methods 0.000 description 6
- 238000013461 design Methods 0.000 description 6
- 238000012544 monitoring process Methods 0.000 description 6
- 230000002159 abnormal effect Effects 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 5
- 230000007613 environmental effect Effects 0.000 description 5
- 230000001360 synchronised effect Effects 0.000 description 5
- 230000032683 aging Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000007789 gas Substances 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000012098 association analyses Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 210000000170 cell membrane Anatomy 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000018044 dehydration Effects 0.000 description 1
- 238000006297 dehydration reaction Methods 0.000 description 1
- 235000019800 disodium phosphate Nutrition 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000007620 mathematical function Methods 0.000 description 1
- 239000012528 membrane Substances 0.000 description 1
- 230000010355 oscillation Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000036647 reaction Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
Landscapes
- Fuel Cell (AREA)
Abstract
The invention provides a fault diagnosis method and a fault diagnosis system for a fuel cell standby power system, which relate to the technical field of fault detection, wherein the method comprises the following steps: collecting operation data; establishing a state space model of a fuel cell standby power system; establishing fuzzy sets of each operation data based on the state space model; based on the fuzzy set, establishing a plurality of local models of each state variable under different fuzzy rules; establishing an interval observer of each state variable meeting the fuzzy rule based on the parameter uncertainty of the TS model; collecting real-time operation data and real-time system input; taking the real-time electric pile working current as the input of an interval observer, and outputting a prediction interval of each operation data; and under the condition that the real-time operation data is positioned in the prediction interval, outputting the operation data normally, otherwise, outputting the operation data abnormally, and sending out early warning. Under the condition that the system is ensured to be in a normal operation range, the fault diagnosis accuracy is increased, and the shutdown frequency caused by misdiagnosis is reduced.
Description
Technical Field
The invention relates to the technical field of fault detection, in particular to a fault diagnosis method and system for a fuel cell standby power system.
Background
The main part of the fuel cell backup power system is a device for directly converting chemical energy into electric energy, generating electric power through chemical reaction rather than combustion, and its working principle is to catalyze the reaction of hydrogen and oxygen between electrodes to generate electric power, water and heat. In operation, the fuel cell consumes oxygen and hydrogen in accordance with the current demand of the electrical load and generates water and heat, the hydrogen being provided by a hydrogen supply system, the main components of which include a pressurized hydrogen storage tank and a supply servo valve for controlling the flow or pressure of the hydrogen. The air supply system consists essentially of a motor driven compressor providing an air flow. The control of the hydrogen and air supply system aims at maintaining the required partial pressure of hydrogen and air entering the anode and cathode of the stack, and furthermore, due to the increased pressure, the air temperature provided by the compressor is higher, the cooling system is used to reduce the air temperature entering the stack to prevent damage to the fuel cell membranes, and finally, the humidifier acts on the cathode path to prevent membrane damage due to dehydration.
The fault detection of the fuel cell standby power system is to monitor and detect the dynamic working process of the fuel cell, and the fault diagnosis of the fuel cell standby power system is important to ensure the high-efficiency and safe operation of the system, so that the fault diagnosis can help to prolong the service life of equipment, reduce the maintenance cost, prevent the larger loss caused by sudden faults, ensure that the system can provide reliable energy support at key moment, and in addition, the systematic fault diagnosis is also helpful to optimize the performance of the fuel cell and improve the energy efficiency and environmental adaptability of the fuel cell.
However, for fault detection of a fuel cell, in the prior art, a fuel cell standby power system with a nonlinear state is often described as a configurable linear system, and then an accurate parameter value is calculated under the linear system to determine whether a fault exists, and in this process, the influence of a nonlinear relation and a non-external factor exists, so that the deviation between the calculated parameter value and a normal operation parameter value is large, the inaccuracy of a calculation result results in inaccurate diagnosis results, and further false alarms frequently occur, so that complete and accurate fault diagnosis is difficult under the condition of ensuring the safety of the system.
Disclosure of Invention
In order to solve the technical problems that in the prior art, a fuel cell standby power system with a nonlinear state is often described as a configurable linear system, and then an accurate parameter value is calculated under the linear system to judge whether a fault exists, the calculated parameter value has larger deviation from a normal operation parameter value due to the influence of a nonlinear relation in the process, the inaccuracy of a calculation result causes inaccuracy of a diagnosis result, false alarm frequently occurs, and complete and accurate fault diagnosis is difficult under the condition of ensuring the safety of the system, the invention provides a fault diagnosis method and a fault diagnosis system of the fuel cell standby power system.
The technical scheme provided by the embodiment of the invention is as follows:
First aspect
The fault diagnosis method for the fuel cell standby power system provided by the embodiment of the invention comprises the following steps:
S1: collecting operation data about a fuel cell backup power system, wherein the operation data comprises a pile working current;
S2: based on the operation data, establishing a state space model of the fuel cell standby power system;
s3: establishing fuzzy sets of each operation data based on the state space model, wherein the fuzzy sets define fuzzy rules of the operation data, and each fuzzy rule is used for describing the membership degree of the operation data in a normal state;
s4: based on fuzzy sets, taking the operating current of a galvanic pile as system input, taking each operating data as a state variable, and establishing a plurality of local models of each state variable under different fuzzy rules, wherein weighting all the local models to obtain TS models describing the operating data of the fuel cell standby power system;
s5: establishing an interval observer of each state variable meeting the fuzzy rule based on the parameter uncertainty of the TS model;
S6: collecting real-time operation data and real-time system input, namely real-time pile working current;
s7: taking the real-time electric pile working current as the input of an interval observer, and outputting a prediction interval of each operation data;
S8: and under the condition that the real-time operation data is positioned in the prediction interval, outputting the operation data normally, otherwise, outputting the operation data abnormally, and sending out early warning.
Second aspect
The fault diagnosis system of the fuel cell standby power system provided by the embodiment of the invention comprises:
A processor;
A memory having stored thereon computer readable instructions which, when executed by the processor, implement the fuel cell backup power system fault diagnosis method of the first aspect.
Third aspect of the invention
An embodiment of the present invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the fuel cell backup power system fault diagnosis method according to the first aspect.
The technical scheme provided by the embodiment of the invention has the beneficial effects that at least:
In the invention, a nonlinear fuel cell standby power system is described by a linear model of a fuzzy set, nonlinear and external disturbance or external noise is introduced into a TS model with fuzzy attribute in a bounded form, a complex nonlinear system is weighted and combined in a separated linear system form, various uncertainties are added and split, more accurate description is provided than a global nonlinear model, a section observer of each state variable established based on the model outputs a prediction section of a system capable of normally operating under the condition of comprehensively considering the internal and external uncertainties, and a fault is isolated in a section form instead of a single-point prediction value, so that the accuracy is high, the misjudgment rate is low, the fault alarm rate can be effectively reduced in a system safe operating state, the consistency of a fault diagnosis result and an actual fault is increased, and the section prediction mode provides a fault-tolerant space for the system, and frequent alarm conditions caused by environmental changes or component ageing deviating from a nominal value are avoided.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a fault diagnosis method for a fuel cell standby power system according to an embodiment of the present invention;
Fig. 2 is a schematic structural diagram of a fault diagnosis system for a fuel cell backup power system according to an embodiment of the present invention.
Detailed Description
The technical scheme of the invention is described below with reference to the accompanying drawings.
In embodiments of the invention, words such as "exemplary," "such as" and the like are used to mean serving as an example, instance, or illustration. Any embodiment or design described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments or designs. Rather, the term use of an example is intended to present concepts in a concrete fashion. Furthermore, in embodiments of the present invention, the meaning of "and/or" may be that of both, or may be that of either, optionally one of both.
In the embodiments of the present invention, "image" and "picture" may be sometimes used in combination, and it should be noted that the meaning of the expression is consistent when the distinction is not emphasized. "of", "corresponding (corresponding, relevant)" and "corresponding (corresponding)" are sometimes used in combination, and it should be noted that the meaning of the expression is consistent when the distinction is not emphasized.
In embodiments of the present invention, sometimes a subscript such as W 1 may be wrongly written in a non-subscript form such as W1, and the meaning of the expression is consistent when the distinction is not emphasized.
In order to make the technical problems, technical solutions and advantages to be solved more apparent, the following detailed description will be given with reference to the accompanying drawings and specific embodiments.
Referring to fig. 1 of the specification, a schematic flow chart of a fault diagnosis method for a fuel cell backup power system according to an embodiment of the invention is shown.
The embodiment of the invention provides a fault diagnosis method of a fuel cell standby power system, which can be realized by fault diagnosis equipment of the fuel cell standby power system, wherein the fault diagnosis equipment of the fuel cell standby power system can be a terminal or a server. The process flow of the fault diagnosis method of the fuel cell backup power system may include the steps of:
s1: operational data is collected regarding a fuel cell backup power system.
Wherein the operational data includes a stack operating current.
The operation data is operation data of an operation point required to perform fault diagnosis, the operating current of the electric pile is an important parameter of the battery in a normal operation state, the operation data is not the input current in the traditional sense for supplying power to the battery, but the current related in the process of generating electric energy through the chemical reaction of hydrogen and oxygen, namely the current generated in the battery in the process of converting the chemical energy into the electric energy, and the current is a key variable in a measurement or control system for monitoring and adjusting the operation state of the fuel battery so as to ensure the optimization of the battery performance and safe and stable operation.
In one possible embodiment, the operational data further includes cathode oxygen quality, anode hydrogen quality, cathode nitrogen quality, supply manifold pressure, return manifold pressure, compressor speed, anode water quality, and cathode water quality.
Operational data is collected by the multimodal sensor.
Wherein the supply manifold and the return manifold are key components for directing the flow of gas, the supply manifold being responsible for delivering hydrogen and oxygen (or air) from an external supply system to the reaction zone of the fuel cell. The return manifold functions to collect and conduct gases not fully consumed after the fuel cell reaction from the fuel cell stack.
S2: based on the operational data, a state space model of the fuel cell backup power system is established.
It should be noted that, the establishment of the state space model is a basis of establishing a TS model, and is a pre-fuzzy condition of the TS model, and on the basis that the pre-fuzzy condition is established, a TS model conforming to the actual situation is further established, so that the complex nonlinear fuel cell is split into an interpretable linear system, and then weighted and combined, so as to accurately consider different uncertainty relations. The creation of the model provides a mathematical framework for the system that can describe and analyze the dynamic behavior of the system and its relationship to the inputs. By the model, a complex nonlinear system can be dynamically converted into a fuzzy linear representation which is easier to analyze and understand, so that an accurate basis is provided for diagnosis.
In one possible implementation, the state space model is specifically:
wherein, AndRespectively represent cathode oxygen massRate of change of anode hydrogen massRate of change of (c) and cathode nitrogen massIs used for the rate of change of (a),Representing supply manifold air qualityIs used for the rate of change of (a),Representing supply manifold pressureIs used for the rate of change of (a),Representing return manifold pressureIs used for the rate of change of (a),Representing compressor speedIs used for the rate of change of (a),Indicating the quality of anode waterIs used for the rate of change of (a),Indicating cathode water qualityIs used for the rate of change of (a),Representing an incidence matrix having a linear relationship with the operational data and having a connection relationship,Representing an associated matrix directly related to said input current, i.e. said stack operating current, T representing a transpose,The stack operating current of the fuel cell, i.e., the input current, is represented.
In particular, the method comprises the steps of,
Each element of which represents an associated matrix in which state variables, i.e., operational data, of a conventional fuel cell have a linearization relationship.
Wherein each element represents an i-th parameter directly related to the input current, i.e. the effect of the input current on the operating data, wherein the two matrices are similar to the matrix elementsThe numbered elements of (a) are expressed as a function of input current, similar toThe elements of the fuel cell backup power system that are not numbered are represented as constants, the subscript represents the row and column positions of the matrix, the interactions and dependencies between the different system state variables are described, and a 0 in the matrix represents that there is no direct linear relationship between these particular rows and columns, so it can be seen that the dynamics of the fuel cell backup power system can be approximated as a linear system, where most of the interactions are described by fixed coefficients, but the dynamics related to the system inputs are parameterized, i.e., each different value of the input current may result in a different set of coefficients in the coefficient matrix, depending on the input current, allowing the model to have different dynamic behavior at different operational data.
It should be noted that, by establishing a fuzzy state space model to comprehensively analyze and predict key operation parameters of the system, the model covers a plurality of key indexes from the mass change rate of oxygen and hydrogen to the speed of the compressor, and the whole scheme is established based on the fuzzy state, so that some parameters in the state space model can be set to be in the fuzzy state, specific relations can be captured or not be set, the design of the model utilizes a linear correlation matrix to describe direct connection among the parameters, and meanwhile, the influence of the operating current of the galvanic pile on the parameters is particularly emphasized. Through the parameterization method, each different input current value can cause coefficient change in the model, so that the behavior of the system under different working conditions can be accurately captured, and accurate dynamic response and prediction capability are provided for fault diagnosis.
S3: a fuzzy set of each operational data is established based on the state space model.
The fuzzy set defines fuzzy rules of the operation data, and each fuzzy rule is used for describing the membership degree of the operation data in a normal state.
Wherein the fuzzy set is a tool for describing the state of each operating parameter of the fuel cell system, which allows a range of parameter values rather than a fixed point, so that the system can handle uncertainties and ambiguities in actual operation. Fuzzy rules are logical rules defined based on these fuzzy sets to describe the relationship between parameter states and system behavior, such as system states that may be manifested when the value of a certain parameter is under a certain degree of membership. The degree of membership is a measure of the state of a quantized parameter representing the position of that parameter relative to the normal operating range.
The membership degree can be simply set to be low, medium and high, and can be quantified by using a specific mathematical function (such as triangle or trapezoid membership function), so that the system can be more flexible and adaptive in the process of uncertainty.
For example, the degree of membership may be further divided into, for cathode oxygen quality, low representing cathode oxygen quality below 25% of normal operating range. Represents cathode oxygen quality between 25% and 75% of the normal operating range. High represents cathode oxygen quality exceeding 75% of normal operating range. For anode hydrogen quality, low represents anode hydrogen quality below 20% of the normal operating range. Represents an anode hydrogen mass of between 20% and 80% of the normal operating range. High represents an anode hydrogen mass exceeding 80% of the normal operating range. A low nitrogen mass for the cathode represents a cathode nitrogen mass below 30% of the normal operating range. Represents a cathode nitrogen mass between 30% and 70% of the normal operating range. High represents cathode nitrogen quality exceeding 70% of normal operating range. The fuzzy rule is that if the cathode oxygen quality is low, there may be a problem of insufficient oxygen supply. If the anode hydrogen quality is high, there may be hydrogen leakage or control failure. If the compressor speed is low and the supply manifold pressure is low, the compressor efficiency may be reduced, other operation data are similar, fuzzy rules among the operation data can be obtained by performing association analysis by combining a state space model in the whole fuzzy set establishment process, and the membership degree can be classified according to a triangle or trapezoid membership function or the membership degree can be customized according to the operation state of the system.
S4: based on the fuzzy set, the operating current of the electric pile is used as the system input, each operation data is used as a state variable, and a plurality of local models of each state variable under different fuzzy rules are built.
Wherein all local models are weighted to obtain a TS model describing the operational data of the fuel cell backup power system.
The local model is based on simplified models of the system under different operation states, and each model corresponds to a specific fuzzy rule. These models are designed based on system inputs (e.g., stack operating current) and various possible system conditions (e.g., oxygen or hydrogen quality, etc.). The local model can reflect different system responses according to actual operating conditions of the system, providing a specific output prediction for each situation. For example, if the model is for a high compressor speed versus low supply manifold pressure, it predicts system performance for this particular condition.
The TS model (Takagi-Sugeno model) is a fuzzy model widely used for nonlinear system control and fault diagnosis, which decomposes complex nonlinear behavior into several local linear models, each model being adapted to a specific operation section of the system, and describes the behavior of the entire fuel cell system by integrating the outputs of all the local models. The model can dynamically capture the accurate behavior of the system in different states by weighting the outputs of the various local models, so that the TS model provides accurate predictions and fault diagnostics even in the face of complex and nonlinear system dynamics.
In general, the local model provides a description of the behavior of the system under certain conditions, while the TS model integrates these descriptions, providing a comprehensive system behavior model that allows for more efficient and accurate monitoring and fault diagnosis of the fuel cell system. In this step, using the fuzzy set obtained from step S3, we take the stack operating current as the system input and build an independent local model for each operating data. These models capture the system behavior under specific conditions and then form a comprehensive TS model by weighting the outputs of these local models. This TS model can dynamically describe the behavior of the fuel cell system in different operating conditions, making the monitoring and fault diagnosis of the system more accurate and efficient. By the method, the system can accurately predict the state change on a real-time basis and timely discover and diagnose potential faults, so that the optimal operation and safety of the system are ensured.
In one possible implementation, the TS model is specifically:
wherein, AndRepresenting the system inputs and state variables at time k,Representing the system output corresponding to the ith fuzzy rule at the moment k, namely the corresponding output value of the state variable under the influence of the system input,A state variable representing the time k +1,Representing the first state transition matrix without fuzzy rules i.e. without uncertain influence,Representing a second state transition matrix with an uncertain influence,AndRepresenting the upper bound of the second state transition matrix and the lower bound of the second state transition matrix respectively,Representing an input matrix for the system input under the ith fuzzy rule derived by the state space model, C representing an output matrix derived by the state space model,Represents the measurement noise at time k, N represents the total number of the fuzzy rules,The set of ambiguities is represented by a set of ambiguities,Representing the ith fuzzy ruleIs used for the degree of membership of the group (a),Representing the ith fuzzy ruleIs a weight of (2).
It should be noted that in the fuel cell backup power system, the TS model handles uncertainty and dynamic changes by combining fuzzy logic, thereby providing more accurate fault diagnosis. This model utilizes a plurality of local models, each model corresponding to a particular fuzzy rule defined in accordance with the current inputs and states of the system. The system inputs and state variables are weighted by the weights of the fuzzy rules to produce a comprehensive system output reflecting the expected behavior in the current state. In addition, the model also considers uncertainty factors, and uses upper and lower matrices to describe potential maximum and minimum system responses, ensuring that the system is still stable in the face of input fluctuations and external disturbances. By the method, the TS model can dynamically adjust the reaction, optimize the accuracy of fault detection and prediction, and greatly enhance the reliability and safety of the system.
S5: based on the parameter uncertainty of the TS model, an interval observer of each state variable meeting the fuzzy rule is established.
The estimation interval describes the range in which the system can normally operate, and includes all possible state values, so that the system is allowed to continue to operate effectively when uncertainty exists, and the situation that the system has no redundancy state caused by precisely limiting the detailed value of the state variable and cannot operate is avoided. The TS interval observer based on the regional space design can provide upper and lower boundary estimation of states under the condition of limited uncertainty and interference, and can effectively detect abnormal fault problems while ensuring normal operation of a system.
It should be noted that, based on the parameter uncertainty of the TS model constructed in the previous step, the interval observers are designed to generate the estimated intervals of each state variable, and these interval observers can provide the upper bound and lower bound estimates of the state variable in consideration of the internal and external uncertainties of the model, by this method, the system can continue to operate reliably even in the face of fluctuations and external disturbances of the input data, effectively isolating and diagnosing faults, and greatly improving the stability and reliability of the system.
In one possible implementation, the interval observer is specifically:
wherein, AndRespectively representing an upper boundary of a state vector and a lower boundary of the state vector at the time k under the ith fuzzy rule,AndRespectively represent the upper boundary and the lower boundary of the state vector at the time k+1 under the ith fuzzy rule,AndRepresenting the upper and lower state vector bounds respectively,AndThe upper and lower interval observer gain bounds are represented respectively,AndRespectively representing an upper bound of a non-negative second state transition matrix, an upper bound of a negative second state transition matrix, a lower bound of the non-negative second state transition matrix and a lower bound of the negative second state transition matrix,AndRepresenting the non-negative state vector upper bound, the non-negative state vector lower bound and the non-negative state vector lower bound, respectively,The representation takes the absolute value of the value,Representing the dimension as the overall dimension of the system outputIs a column vector of 1.
Wherein the non-negative second state transition matrix retains only the 0-valued and positive portions of the matrix, and the negative second state transition matrix retains only the negative portions of the matrix.
Among them, the inter-zone observer is a key component in the fuel cell backup power system, which enhances reliability of fault diagnosis by taking into consideration a possible range of variation of system states. The observer uses fuzzy rules to determine the upper and lower bounds of the state variables, providing a prediction interval for the real-time state of the system. By calculating the upper and lower bounds of the gain, and processing the non-negative and negative portions of the state transition matrix, the interval observer is able to accurately capture the dynamic behavior of the system in normal and fault states. The method enables the system to effectively predict and adjust the response of the system in the face of input uncertainty and external disturbance, thereby ensuring the stability and safety of operation and reducing the risk and influence of system faults.
In one possible implementation, the upper range observer gain bound and the lower range observer gain bound are specifically:
wherein, AndRespectively representing block diagonal matrices derived based on a linear time invariant theory for the ith fuzzy ruleUpper block diagonal matrix boundaries and lower block diagonal matrix boundaries,Represents the inverse of the diagonal matrix P, which is derived based on the linear time invariant theory, Q represents the symmetric matrix which is derived based on the linear time invariant theory,AndAll represent constants greater than zero, T represents the transpose,Representing a function taken for all fuzzy rulesThe maximum value of the number of the first and second sets,Representing the two-norm operator,AndAll represent intermediate quantities.
Where observer gain is a parameter in the observer used for system state estimation that determines the intensity and speed of the transition from measured data to state estimation. Specifically, the gain affects the response speed of the system to the input signal and the sensitivity to errors or noise, which are key factors in optimizing the performance and stability of the system.
The observer gain upper bound and observer gain lower bound define the range over which these gains may vary. Ideally, the gain should be selected to enable the system to track state changes quickly and accurately while suppressing errors due to model inaccuracies or external noise. The setting of the upper and lower limits of the gain ensures that the observer operates without exceeding these limits, thereby preventing oscillations or unstable behavior due to the gain being too high while effectively tracking the system state.
The upper and lower bounds of the observer gain based on the linear time invariant theorem and the stability analysis of the diagonal matrix allow the system to maintain the dynamic accurate control under the framework of the fuzzy logic, and various operating conditions are adapted by adjusting the upper and lower bounds of the gain. The use of the inverse and symmetric matrices of the diagonal matrix, and the associated constants, ensures optimization of observer gain, thereby enabling the system to maintain efficient and stable performance even in a complex varying environment, and the application of this technique significantly improves the fault diagnosis capability of the fuel cell system, ensuring the reliability and safety of the system.
S6: and collecting real-time operation data and real-time system input, namely real-time pile working current.
It can be understood that collecting real-time operation data and operating current of the electric pile is a data base for ensuring efficient monitoring and fault diagnosis of the fuel cell backup power system, and by continuously tracking the key data, we can capture the operation state of the system in real time and respond to potential abnormal changes in time. The real-time data acquisition mechanism ensures the adaptability and the response speed of the system in a dynamic environment, provides necessary data support for subsequent fault analysis, and enhances the safety and the reliability of the whole system.
S7: and taking the real-time electric pile working current as the input of an interval observer, and outputting a prediction interval of each operation data.
Where the prediction interval is a concept for estimating the range of values within which future observations may fall.
The method provides an upper bound and a lower bound for possible future values, so that the estimation of the future state of the system has a certain confidence interval, and in fault diagnosis and system monitoring, the possible performance of the system under normal operation and abnormal states can be predicted by determining a prediction interval, and the interval not only reflects the prediction uncertainty, but also can be used for detecting the abnormal value or the change of the trend of the system, thereby being beneficial to timely adjustment or maintenance and ensuring the stable operation of the system.
In one possible embodiment, the prediction interval is specifically:
wherein, AndThe upper system output bound at time k and the lower system output bound at time k are respectively represented,Representing a non-negative output matrix consisting of zero values and positive values of the output matrix C,Representing the negative output matrix resulting from the extraction of the negative values in the output matrix C.
The prediction interval is the possible range of the system output, that is, the maximum possible fluctuation range of the output value obtained at each time. The use of non-negative and negative output matrices further refines these boundaries, ensuring that the predictions cover all possible output scenarios, thus allowing the system to maintain accuracy and reliability of predictions in the face of internal variations and external disturbances.
S8: and under the condition that the real-time operation data is positioned in the prediction interval, outputting the operation data normally, otherwise, outputting the operation data abnormally, and sending out early warning.
It should be noted that, the system determines the device status by comparing the operation data with the prediction interval in real time. If the real-time data falls in the prediction interval, the system is indicated to run normally, and no fault occurs. Otherwise, if the data exceeds the prediction interval, the system determines that the data is abnormal and immediately sends out early warning. The mechanism effectively enhances the reliability and safety of the system, and can timely identify and respond to potential problems, thereby avoiding larger equipment damage or downtime and ensuring continuous and stable operation.
In one possible implementation, after S8, the method further includes:
And updating the fuzzy set at intervals of a preset duration.
It will be appreciated that it is vital to update the fuzzy sets periodically during the operation of the system. This ensures that the model remains synchronized with the current operating environment, adapts to possible changes or new operating conditions, thereby enhancing the accuracy and reliability of the diagnosis, and this periodic assessment and adjustment method helps to continuously optimize system performance and prevent potential failure.
In the practical application process, the fault diagnosis method starts from collecting key operation data of a fuel cell standby power system, constructs a state space model based on the data, and further establishes a fuzzy set to describe the membership degree of the operation data. Through fuzzy logic, multiple local models are created for each state variable, these models are integrated into one TS model, and an interval observer is built based on this model to monitor the system state. The continuous collection and the real-time monitoring of the real-time data ensure that the system can respond to any abnormality immediately, and finally, early warning is sent out when the operation data exceeds the normal range, so that the stability and the safety of the system are ensured, and the accuracy and the response speed of diagnosis are improved.
The technical scheme provided by the embodiment of the invention has the beneficial effects that at least:
In the invention, a nonlinear fuel cell standby power system is described by a linear model of a fuzzy set, nonlinear and external disturbance or external noise is introduced into a TS model with fuzzy attribute in a bounded form, a complex nonlinear system is weighted and combined in a separated linear system form, various uncertainties are added and split, more accurate description is provided than a global nonlinear model, a section observer of each state variable established based on the model outputs a prediction section of a system capable of normally operating under the condition of comprehensively considering the internal and external uncertainties, and a fault is isolated in a section form instead of a single-point prediction value, so that the accuracy is high, the misjudgment rate is low, the fault alarm rate can be effectively reduced in a system safe operating state, the consistency of a fault diagnosis result and an actual fault is increased, and the section prediction mode provides a fault-tolerant space for the system, and frequent alarm conditions caused by environmental changes or component ageing deviating from a nominal value are avoided.
Referring to fig. 2 of the specification, a schematic structural diagram of a fault diagnosis system for a fuel cell backup power system according to the present invention is shown.
The invention also provides a fault diagnosis system 20 of the fuel cell standby power system, which is applied to the fault diagnosis method of the fuel cell standby power system, and comprises the following steps:
A processor 201.
The memory 202 has stored thereon computer readable instructions which, when executed by the processor 201, implement a method for diagnosing a fault in a fuel cell backup power system as in the method embodiment.
The fault diagnosis system 20 for a fuel cell backup power system provided by the present invention can execute the above fault diagnosis method for a fuel cell backup power system and achieve the same or similar technical effects, and in order to avoid repetition, the present invention is not repeated.
The technical scheme provided by the embodiment of the invention has the beneficial effects that at least:
In the invention, a nonlinear fuel cell standby power system is described by a linear model of a fuzzy set, nonlinear and external disturbance or external noise is introduced into a TS model with fuzzy attribute in a bounded form, a complex nonlinear system is weighted and combined in a separated linear system form, various uncertainties are added and split, more accurate description is provided than a global nonlinear model, a section observer of each state variable established based on the model outputs a prediction section of a system capable of normally operating under the condition of comprehensively considering the internal and external uncertainties, and a fault is isolated in a section form instead of a single-point prediction value, so that the accuracy is high, the misjudgment rate is low, the fault alarm rate can be effectively reduced in a system safe operating state, the consistency of a fault diagnosis result and an actual fault is increased, and the section prediction mode provides a fault-tolerant space for the system, and frequent alarm conditions caused by environmental changes or component ageing deviating from a nominal value are avoided.
It should be appreciated that the processor in embodiments of the invention may be a central processing unit (central processing unit, CPU), which may also be other general purpose processors, digital signal processors (DIGITAL SIGNAL processors, DSPs), application Specific Integrated Circuits (ASICs), off-the-shelf programmable gate arrays (field programmable GATE ARRAY, FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
It should also be appreciated that the memory in embodiments of the present invention may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The nonvolatile memory may be a read-only memory (ROM), a Programmable ROM (PROM), an erasable programmable ROM (erasable PROM), an electrically erasable programmable EPROM (EEPROM), or a flash memory. The volatile memory may be random access memory (random access memory, RAM) which acts as external cache memory. By way of example, and not limitation, many forms of random access memory (random access memory, RAM) are available, such as static random access memory (STATIC RAM, SRAM), dynamic Random Access Memory (DRAM), synchronous Dynamic Random Access Memory (SDRAM), double data rate synchronous dynamic random access memory (double DATA RATE SDRAM, DDR SDRAM), enhanced synchronous dynamic random access memory (ENHANCED SDRAM, ESDRAM), synchronous link dynamic random access memory (SYNCHLINK DRAM, SLDRAM), and direct memory bus random access memory (direct rambus RAM, DR RAM).
The above embodiments may be implemented in whole or in part by software, hardware (e.g., circuitry), firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions described in accordance with embodiments of the present invention are produced in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains one or more sets of available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium may be a solid state disk.
It should be understood that the term "and/or" is merely an association relationship describing the associated object, and means that three relationships may exist, for example, a and/or B may mean: there are three cases, a alone, a and B together, and B alone, wherein a, B may be singular or plural. In addition, the character "/" herein generally indicates that the associated object is an "or" relationship, but may also indicate an "and/or" relationship, and may be understood by referring to the context.
In the present invention, "at least one" means one or more, and "a plurality" means two or more. "at least one of" or the like means any combination of these items, including any combination of single item(s) or plural items(s). For example, at least one (one) of a, b, or c may represent: a, b, c, a-b, a-c, b-c, or a-b-c, wherein a, b, c may be single or plural.
It should be understood that, in various embodiments of the present invention, the sequence numbers of the foregoing processes do not mean the order of execution, and the order of execution of the processes should be determined by the functions and internal logic thereof, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
It will be clearly understood by those skilled in the art that, for convenience and brevity of description, specific working procedures of the apparatus, device and unit described above may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
In the several embodiments provided by the present invention, it should be understood that the disclosed apparatus, device and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another device, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (random access memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
An embodiment of the present invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the fuel cell backup power system fault diagnosis method according to the method embodiment.
The computer readable storage medium provided by the invention can realize the steps and effects of the fault diagnosis method of the fuel cell standby power system in the embodiment of the method, and the invention is not repeated for avoiding repetition.
The technical scheme provided by the embodiment of the invention has the beneficial effects that at least:
In the invention, a nonlinear fuel cell standby power system is described by a linear model of a fuzzy set, nonlinear and external disturbance or external noise is introduced into a TS model with fuzzy attribute in a bounded form, a complex nonlinear system is weighted and combined in a separated linear system form, various uncertainties are added and split, more accurate description is provided than a global nonlinear model, a section observer of each state variable established based on the model outputs a prediction section of a system capable of normally operating under the condition of comprehensively considering the internal and external uncertainties, and a fault is isolated in a section form instead of a single-point prediction value, so that the accuracy is high, the misjudgment rate is low, the fault alarm rate can be effectively reduced in a system safe operating state, the consistency of a fault diagnosis result and an actual fault is increased, and the section prediction mode provides a fault-tolerant space for the system, and frequent alarm conditions caused by environmental changes or component ageing deviating from a nominal value are avoided.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
The following points need to be described:
(1) The drawings of the embodiments of the present invention relate only to the structures related to the embodiments of the present invention, and other structures may refer to the general designs.
(2) In the drawings for describing embodiments of the present invention, the thickness of layers or regions is exaggerated or reduced for clarity, i.e., the drawings are not drawn to actual scale. It will be understood that when an element such as a layer, film, region or substrate is referred to as being "on" or "under" another element, it can be "directly on" or "under" the other element or intervening elements may be present.
(3) The embodiments of the invention and the features of the embodiments can be combined with each other to give new embodiments without conflict.
The present invention is not limited to the above embodiments, but the scope of the invention is defined by the claims.
Claims (10)
1. A fault diagnosis method of a fuel cell backup power system, comprising:
s1: collecting operation data about the fuel cell backup power system, wherein the operation data comprises a pile operating current;
s2: based on the operation data, establishing a state space model of the fuel cell standby power system;
s3: establishing fuzzy sets of each operation data based on the state space model, wherein the fuzzy sets define fuzzy rules of the operation data, and each fuzzy rule is used for describing the membership degree of the operation data in a normal state;
S4: based on the fuzzy set, taking the operating current of the electric pile as system input, taking each operating data as a state variable, and establishing a plurality of local models of each state variable under different fuzzy rules, wherein all the local models are weighted to obtain a TS model describing the operating data of the fuel cell standby power system;
S5: establishing an interval observer of each state variable meeting the fuzzy rule based on the parameter uncertainty of the TS model;
S6: collecting real-time operation data and real-time system input, namely real-time pile working current;
s7: taking the real-time electric pile working current as the input of the interval observer, and outputting a prediction interval of each operation data;
S8: and under the condition that the real-time operation data is positioned in the prediction interval, outputting the operation data normally, otherwise, outputting the operation data abnormally and sending out early warning.
2. The fuel cell backup power system fault diagnosis method of claim 1, wherein the operation data further comprises cathode oxygen quality, anode hydrogen quality, cathode nitrogen quality, supply manifold pressure, return manifold pressure, compressor speed, anode water quality, and cathode water quality;
And acquiring the operation data through a multi-mode sensor.
3. The method for diagnosing a fault in a fuel cell backup power system according to claim 2, wherein the state space model is specifically:
wherein, AndRespectively represent cathode oxygen massRate of change of anode hydrogen massRate of change of (c) and cathode nitrogen massIs used for the rate of change of (a),Representing supply manifold air qualityIs used for the rate of change of (a),Representing supply manifold pressureIs used for the rate of change of (a),Representing return manifold pressureIs used for the rate of change of (a),Representing compressor speedIs used for the rate of change of (a),Indicating the quality of anode waterIs used for the rate of change of (a),Indicating cathode water qualityIs used for the rate of change of (a),Representing an incidence matrix having a linear relationship with the operational data and having a connection relationship,Representing an associated matrix directly related to the input current, i.e. the operating current of the stack, T representing the transpose,The stack operating current of the fuel cell, i.e., the input current, is represented.
4. The fault diagnosis method for a fuel cell backup power system according to claim 1, wherein the TS model is specifically:
wherein, AndRepresenting the system inputs and state variables at time k,Representing the system output corresponding to the ith fuzzy rule at the moment k, namely the corresponding output value of the state variable under the influence of the system input,A state variable representing the time k +1,Representing the first state transition matrix without fuzzy rules i.e. without uncertain influence,Representing a second state transition matrix with an uncertain influence,AndRepresenting the upper bound of the second state transition matrix and the lower bound of the second state transition matrix respectively,Representing an input matrix for the system input under the ith fuzzy rule derived by the state space model, C representing an output matrix derived by the state space model,Represents the measurement noise at time k, N represents the total number of the fuzzy rules,The set of ambiguities is represented by a set of ambiguities,Representing the ith fuzzy ruleIs used for the degree of membership of the group (a),Representing the ith fuzzy ruleIs a weight of (2).
5. The fault diagnosis method for a fuel cell backup power system according to claim 1, wherein the section observer is specifically:
wherein, AndRespectively representing an upper boundary of a state vector and a lower boundary of the state vector at the time k under the ith fuzzy rule,AndRespectively represent the upper boundary and the lower boundary of the state vector at the time k+1 under the ith fuzzy rule,AndRepresenting the upper and lower state vector bounds respectively,AndThe upper and lower interval observer gain bounds are represented respectively,AndRespectively representing an upper bound of a non-negative second state transition matrix, an upper bound of a negative second state transition matrix, a lower bound of the non-negative second state transition matrix and a lower bound of the negative second state transition matrix,AndRespectively represent a non-negative state vector upper bound, a non-negative state vector lower bound and a non-negative state vector lower bound,The representation takes the absolute value of the value,Representing the dimension as the overall dimension of the system outputIs a column vector of 1.
6. The method for diagnosing a fault in a fuel cell backup power system according to claim 5, wherein the interval observer gain upper bound and the interval observer gain lower bound are specifically:
wherein, AndRespectively representing block diagonal matrices derived based on a linear time invariant theory for the ith fuzzy ruleUpper block diagonal matrix boundaries and lower block diagonal matrix boundaries,Represents the inverse of the diagonal matrix P, which is derived based on the linear time invariant theory, Q represents the symmetric matrix which is derived based on the linear time invariant theory,AndAll represent constants greater than zero, T represents the transpose,Representing a function taken for all fuzzy rulesThe maximum value of the number of the first and second sets,Representing the two-norm operator,AndAll represent intermediate quantities.
7. The method for diagnosing a fault in a fuel cell backup power system according to claim 5, wherein the prediction interval is specifically:
wherein, AndThe upper system output bound at time k and the lower system output bound at time k are respectively represented,Representing a non-negative output matrix consisting of zero values and positive values of the output matrix C,Representing the negative output matrix resulting from the extraction of the negative values in the output matrix C.
8. The fault diagnosis method of a fuel cell backup power system according to claim 1, further comprising, after said S8:
And updating the fuzzy set at intervals of a preset duration.
9. A fuel cell backup power system fault diagnosis system, comprising:
A processor;
a memory having stored thereon computer readable instructions which, when executed by the processor, implement the fuel cell backup power system fault diagnosis method of any one of claims 1 to 8.
10. A computer-readable storage medium having stored thereon a computer program, wherein the program when executed by a processor implements the fuel cell backup power system failure diagnosis method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411162089.1A CN118693312A (en) | 2024-08-23 | 2024-08-23 | Fault diagnosis method and system for fuel cell standby power system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411162089.1A CN118693312A (en) | 2024-08-23 | 2024-08-23 | Fault diagnosis method and system for fuel cell standby power system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118693312A true CN118693312A (en) | 2024-09-24 |
Family
ID=92778297
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411162089.1A Pending CN118693312A (en) | 2024-08-23 | 2024-08-23 | Fault diagnosis method and system for fuel cell standby power system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118693312A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107479389A (en) * | 2017-09-30 | 2017-12-15 | 东南大学 | A kind of fired power generating unit overheating steam temperature predictive fuzzy Adaptive PID Control method |
| CN109212974A (en) * | 2018-11-12 | 2019-01-15 | 辽宁石油化工大学 | The robust fuzzy of Interval time-varying delay system predicts fault tolerant control method |
| CN114492087A (en) * | 2022-04-02 | 2022-05-13 | 国网浙江省电力有限公司电力科学研究院 | Fault diagnosis method and device for proton exchange membrane fuel cell of hydrogen energy storage power station |
| CN115799580A (en) * | 2022-12-08 | 2023-03-14 | 合肥综合性国家科学中心能源研究院(安徽省能源实验室) | OS-ELM fuel cell fault diagnosis method based on optimized FCM training |
| US20230419741A1 (en) * | 2022-06-28 | 2023-12-28 | Beta Air, Llc | Assembly and method for gauging fuel of electric aircraft |
| CN117389146A (en) * | 2023-11-09 | 2024-01-12 | 北京建筑大学 | Nonlinear model predictive control system for cooling unit system of data center |
-
2024
- 2024-08-23 CN CN202411162089.1A patent/CN118693312A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107479389A (en) * | 2017-09-30 | 2017-12-15 | 东南大学 | A kind of fired power generating unit overheating steam temperature predictive fuzzy Adaptive PID Control method |
| CN109212974A (en) * | 2018-11-12 | 2019-01-15 | 辽宁石油化工大学 | The robust fuzzy of Interval time-varying delay system predicts fault tolerant control method |
| CN114492087A (en) * | 2022-04-02 | 2022-05-13 | 国网浙江省电力有限公司电力科学研究院 | Fault diagnosis method and device for proton exchange membrane fuel cell of hydrogen energy storage power station |
| US20230419741A1 (en) * | 2022-06-28 | 2023-12-28 | Beta Air, Llc | Assembly and method for gauging fuel of electric aircraft |
| CN115799580A (en) * | 2022-12-08 | 2023-03-14 | 合肥综合性国家科学中心能源研究院(安徽省能源实验室) | OS-ELM fuel cell fault diagnosis method based on optimized FCM training |
| CN117389146A (en) * | 2023-11-09 | 2024-01-12 | 北京建筑大学 | Nonlinear model predictive control system for cooling unit system of data center |
Non-Patent Citations (1)
| Title |
|---|
| DAMIANO ROTONDO.ET AL: "Robust fault diagnosis of proton exchange membrane fuel cells using a Takagi-Sugeno interval observer approach", 《INTERNATIONAL JOURNAL OF HYDROGEN ENERGY》, vol. 41, no. 4, 7 January 2016 (2016-01-07), pages 2875 - 2886, XP029396654, DOI: 10.1016/j.ijhydene.2015.12.071 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Rotondo et al. | Robust fault diagnosis of proton exchange membrane fuel cells using a Takagi-Sugeno interval observer approach | |
| RU2313815C2 (en) | Device and method for controlling technical plant, which contains a set of systems, in particular, electric power plant | |
| US11604934B2 (en) | Failure prediction using gradient-based sensor identification | |
| Kamal et al. | Fault detection and isolation for PEM fuel cell stack with independent RBF model | |
| Yang et al. | A hybrid model-based fault detection strategy for air handling unit sensors | |
| RU2649542C1 (en) | Method and system of remote monitoring of objects | |
| CN110112442B (en) | Fuel cell system control method and device | |
| KR20230036776A (en) | System and method for fault diagnosis of fuel cell energy management system based on digital twin | |
| Venturini et al. | Prediction reliability of a statistical methodology for gas turbine prognostics | |
| CN111597223A (en) | Fault early warning processing method, device and system | |
| CN112884199B (en) | Hydropower station equipment fault prediction method, hydropower station equipment fault prediction device, computer equipment and storage medium | |
| JP7008098B2 (en) | Multi-stage failure diagnosis method and equipment for fuel cell system | |
| Keller et al. | Fault-tolerant model predictive control of a direct methanol-fuel cell system with actuator faults | |
| EP4113539A1 (en) | Method and system for intelligent monitoring of state of nuclear power plant | |
| KR20180024333A (en) | Device abnormality presensing method and system using thereof | |
| CN111624986A (en) | Case base-based fault diagnosis method and system | |
| KR20120096614A (en) | Method for detecting fail of hydrogen supply system for fuel cell | |
| CN117523793A (en) | Power plant equipment fault early warning method and computer equipment | |
| Uren et al. | An integrated approach to sensor FDI and signal reconstruction in HTGRs–Part I: Theoretical framework | |
| CN115632486B (en) | Power consumption safety management method and system based on Internet of things | |
| CN118693312A (en) | Fault diagnosis method and system for fuel cell standby power system | |
| Murshed et al. | Monitoring of solid oxide fuel cell systems | |
| Davari et al. | Fault forecasting using data-driven modeling: a case study for metro do Porto data set | |
| CN116068479A (en) | Abnormality detection method and device for output performance signal in fuel cell endurance test | |
| CN113689042B (en) | Fault source prediction method for monitoring node |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination |