Coupled hydrogen production system fault detection method, device and equipment and storage medium

Abstract

The invention discloses a coupled hydrogen production system fault detection method and device, equipment and a storage medium. The method comprises the steps that monitoring values of preset parameters of all sets of equipment units in a coupled hydrogen production system are obtained; determining a fault index of the coupled hydrogen production system according to the monitoring value of the preset parameter of each group of equipment units; and when the fault index of the coupled hydrogen production system is greater than a first preset threshold value, fault early warning information is sent to a preset terminal. By adopting the scheme provided by the invention, comprehensive fault detection can be carried out on the coupled hydrogen production system of multiple groups of equipment units instead of monitoring a single equipment fault, so that comprehensive fault detection on the coupled hydrogen production system is realized, and the detection efficiency and accuracy are improved.

Description

Technical Field

[0001] The present application relates to the technical field of fault detection, and in particular to a method, device, equipment and storage medium for fault detection of a coupled hydrogen production system. Background Art

[0002] The coupled hydrogen production system is a new type of clean energy production method. The core of this system is to use renewable energy (such as solar energy or wind energy) to drive the electrolysis process and produce hydrogen. The main advantage of the coupled hydrogen production system is that the hydrogen it produces has no carbon emissions and is more environmentally friendly than traditional fossil fuel hydrogen production. In the prior art, the detection methods for hydrogen production system faults are mostly focused on the monitoring of independent equipment layers, such as electrolyzer fault detection. For coupled hydrogen production systems, since they involve multiple groups of equipment units and are designed to integrate multiple energy sources, the detection of a single device cannot meet the fault monitoring needs of the coupled hydrogen production system. Summary of the invention

[0003] The present application provides a coupled hydrogen production system fault detection method, device, equipment and storage medium for performing comprehensive fault detection on a coupled hydrogen production system of multiple devices to improve detection efficiency and accuracy.

[0004] The present application provides a coupled hydrogen production system fault detection method, comprising:

[0005] Obtaining monitoring values ​​of preset parameters of each group of equipment units in the coupled hydrogen production system;

[0006] Determining a fault index of the coupled hydrogen production system according to monitoring values ​​of preset parameters of each group of equipment units;

[0007] When the fault index of the coupled hydrogen production system is greater than a first preset threshold, a fault warning message is sent to a preset terminal.

[0008] The beneficial effects of the present application are: by obtaining the monitoring values ​​of the preset parameters of each group of equipment units in the coupled hydrogen production system; determining the fault index of the coupled hydrogen production system according to the monitoring values ​​of the preset parameters of each group of equipment units; when the fault index of the coupled hydrogen production system is greater than the first preset threshold, sending fault warning information to the preset terminal. Since the preset parameters of multiple groups of equipment units are collected, the coupled hydrogen production system of multiple groups of equipment units can be comprehensively detected for faults, rather than just monitoring the faults of a single device, so as to achieve comprehensive fault detection of the coupled hydrogen production system and improve detection efficiency and accuracy.

[0009] In one embodiment, determining the fault index of the coupled hydrogen production system according to the monitoring values ​​of the preset parameters of each group of equipment units includes:

[0010] Inputting the monitoring values ​​of the preset parameters of each group of equipment units into a preset model to obtain a fault indicator matrix of the coupled hydrogen production system, wherein the fault indicator matrix at least includes equipment performance failure factors, equipment safety failure factors, system-level failure factors and coupling failure factors of each group of equipment units;

[0011] Multiplying the fault index matrix of the coupled hydrogen production system and the fault factor weight to obtain a fault degree vector of the coupled hydrogen production system;

[0012] The weight of each group of equipment units is multiplied by the fault degree vector of the coupled hydrogen production system to obtain a fault index of the coupled hydrogen production system.

[0013] The beneficial effect of this embodiment is that the monitoring values ​​of the preset parameters of each group of equipment units are input into the preset model to obtain the equipment performance fault factor, equipment safety fault factor, system-level fault factor and coupling fault factor of the hydrogen production system, including the fault factor at the equipment level and the fault factor at the system level. Therefore, it not only detects faults at the level of a single equipment, but also includes fault detection at the system level. The accuracy of fault detection of the coupled hydrogen production system is improved.

[0014] In one embodiment, the sending of fault warning information to a preset terminal includes:

[0015] Sort the elements in the fault degree vector from large to small according to their values;

[0016] Determining that the equipment units corresponding to the first preset number of elements in the sorting are faulty equipment units;

[0017] Sending fault warning information including the faulty equipment unit identifier to a preset terminal.

[0018] The beneficial effect of this embodiment is that by sorting the elements in the fault degree vector, the fault degree of each equipment unit is determined, and then the faulty equipment unit is determined, and the faulty equipment unit identification is sent during the fault warning, without the need for manual one-by-one checking, thereby improving the efficiency of fault detection.

[0019] In one embodiment, the sending of fault warning information to a preset terminal includes:

[0020] Comparing the elements in the fault degree vector with the second preset threshold value respectively;

[0021] Determine that the device unit corresponding to the element in the fault degree vector that is greater than a second preset threshold is a faulty device unit;

[0022] Sending fault warning information including the faulty equipment unit identifier to a preset terminal.

[0023] The beneficial effect of this embodiment is that by screening the devices with a fault degree vector greater than a preset threshold, the devices with a higher fault degree are determined to be faulty device units, and the faulty device unit identification is sent during fault warning, without the need for manual investigation one by one, thereby improving the efficiency of fault detection.

[0024] In one embodiment, the method further comprises:

[0025] Sorting the multiple failure factors of the failed equipment unit from large to small according to the numerical values;

[0026] Determine the fault factor with the largest value as the fault cause of the faulty equipment unit;

[0027] The sending of fault warning information to a preset terminal also includes:

[0028] Sending fault warning information including the fault cause to a preset terminal.

[0029] The beneficial effect of this embodiment is that: by analyzing multiple fault factors of the faulty equipment unit, the fault cause of the faulty equipment is determined, and the fault cause is sent during the fault warning, thereby improving the efficiency of fault detection.

[0030] In one embodiment, the device performance failure factor is determined by:

[0031] Obtain monitoring values ​​of production capacity parameters and operating parameters of each group of equipment units;

[0032] Inputting the monitored values ​​of the operating parameters into the first sub-model of the preset model to obtain first predicted values ​​of the production capacity parameters of each group of equipment units;

[0033] The difference between the monitored value of the capacity parameter of each group of equipment units and the first predicted value is taken as the first difference;

[0034] When there is a first equipment unit whose first difference is greater than or equal to a third preset threshold, determining that the equipment performance failure factor of the first equipment unit is the first difference;

[0035] When there is a second equipment unit whose first difference is less than a third preset threshold, determining that the equipment performance failure factor of the second equipment unit is 0;

[0036] The equipment safety failure factor is determined in the following manner:

[0037] Obtain monitoring values ​​of operating parameters and safety parameters of each group of equipment units;

[0038] Inputting the monitored value of the operating parameter into the second sub-model of the preset model to obtain the second predicted value of the safety parameter of each group of equipment units;

[0039] The difference between the monitored value of the safety parameter of each group of equipment units and the second predicted value is used as the second difference;

[0040] When there is a third equipment unit whose second difference is greater than or equal to a fourth preset threshold, determining that the equipment safety failure factor of the third equipment unit is the second difference;

[0041] When there is a fourth equipment unit whose second difference is less than a fourth preset threshold, it is determined that the equipment safety failure factor of the fourth equipment unit is 0.

[0042] In one embodiment, the system-level failure factor is determined by:

[0043] Obtain monitoring values ​​of production capacity parameters, performance parameters, safety parameters, power supply fluctuation parameters and hydrogen production demand of each group of equipment units;

[0044] Inputting the monitoring values ​​of the power supply volatility parameter and the hydrogen production demand into the third sub-model of the preset model, respectively obtaining the predicted values ​​of the production capacity parameter, the production capacity parameter and the safety parameter of each group of equipment units;

[0045] The difference between the monitored value and the predicted value of the capacity parameter, performance parameter and safety parameter of each equipment unit is compared with the corresponding preset threshold value to determine the capacity parameter failure factor, performance parameter failure factor and safety parameter failure factor of each equipment unit;

[0046] The sum of the production capacity parameter failure factor, the performance parameter failure factor and the safety parameter failure factor of each equipment unit is determined as the system-level failure factor of the equipment unit.

[0047] The present application also provides a coupled hydrogen production system fault detection device, comprising:

[0048] An acquisition module, used to acquire monitoring values ​​of preset parameters of each group of equipment units in the coupled hydrogen production system;

[0049] A first determination module, configured to determine a fault index of the coupled hydrogen production system according to monitoring values ​​of preset parameters of each group of equipment units;

[0050] The sending module is used to send fault warning information to a preset terminal when the fault index of the coupled hydrogen production system is greater than a first preset threshold.

[0051] In one embodiment, the determining module includes:

[0052] An input submodule, used to input the monitoring values ​​of the preset parameters of each group of equipment units into a preset model to obtain a fault indicator matrix of the coupled hydrogen production system, wherein the fault indicator matrix at least includes equipment performance failure factors, equipment safety failure factors, system-level failure factors and coupling failure factors of each group of equipment units;

[0053] A first multiplication submodule is used to multiply the fault index matrix of the coupled hydrogen production system and the fault factor weight to obtain a fault degree vector of the coupled hydrogen production system;

[0054] The second multiplication submodule is used to multiply the weight of each group of equipment units by the fault degree vector of the coupled hydrogen production system to obtain a fault index of the coupled hydrogen production system.

[0055] In one embodiment, the sending module includes:

[0056] A first sorting submodule, used to sort the elements in the fault degree vector from large to small according to numerical values;

[0057] A first determination submodule, configured to determine that the equipment units corresponding to the first preset number of elements in the sequence are faulty equipment units;

[0058] The first sending submodule is used to send fault warning information including the faulty equipment unit identifier to a preset terminal.

[0059] In one embodiment, the sending module includes:

[0060] A comparison submodule, used for comparing the elements in the fault degree vector with the second preset threshold value respectively;

[0061] A second determination submodule, configured to determine that a device unit corresponding to an element in the fault degree vector that is greater than a second preset threshold value is a faulty device unit;

[0062] The second sending submodule is used to send the fault warning information including the faulty equipment unit identifier to a preset terminal.

[0063] In one embodiment, the apparatus further comprises:

[0064] A sorting module, used to sort the multiple fault factors of the faulty equipment unit from large to small according to numerical values;

[0065] A second determination module is used to determine the fault factor with the largest value as the fault cause of the faulty equipment unit;

[0066] The sending module is further used for:

[0067] Sending fault warning information including the fault cause to a preset terminal.

[0068] In one embodiment, the device performance failure factor is determined by:

[0069] Obtain monitoring values ​​of production capacity parameters and operating parameters of each group of equipment units;

[0070] Inputting the monitored values ​​of the operating parameters into the first sub-model of the preset model to obtain first predicted values ​​of the production capacity parameters of each group of equipment units;

[0071] The difference between the monitored value of the capacity parameter of each group of equipment units and the first predicted value is taken as the first difference;

[0072] When there is a first equipment unit whose first difference is greater than or equal to a third preset threshold, determining that the equipment performance failure factor of the first equipment unit is the first difference;

[0073] When there is a second equipment unit whose first difference is less than a third preset threshold, determining that the equipment performance failure factor of the second equipment unit is 0;

[0074] The equipment safety failure factor is determined in the following manner:

[0075] Obtain monitoring values ​​of operating parameters and safety parameters of each group of equipment units;

[0076] Inputting the monitored value of the operating parameter into the second sub-model of the preset model to obtain the second predicted value of the safety parameter of each group of equipment units;

[0077] The difference between the monitored value of the safety parameter of each group of equipment units and the second predicted value is used as the second difference;

[0078] When there is a third equipment unit whose second difference is greater than or equal to a fourth preset threshold, determining that the equipment safety failure factor of the third equipment unit is the second difference;

[0079] When there is a fourth equipment unit whose second difference is less than a fourth preset threshold, it is determined that the equipment safety failure factor of the fourth equipment unit is 0.

[0080] In one embodiment, the system-level failure factor is determined by:

[0081] Obtain monitoring values ​​of production capacity parameters, performance parameters, safety parameters, power supply fluctuation parameters and hydrogen production demand of each group of equipment units;

[0082] Inputting the monitoring values ​​of the power supply volatility parameter and the hydrogen production demand into the third sub-model of the preset model, respectively obtaining the predicted values ​​of the production capacity parameter, the production capacity parameter and the safety parameter of each group of equipment units;

[0083] The difference between the monitored value and the predicted value of the capacity parameter, performance parameter and safety parameter of each equipment unit is compared with the corresponding preset threshold value to determine the capacity parameter failure factor, performance parameter failure factor and safety parameter failure factor of each equipment unit;

[0084] The sum of the production capacity parameter failure factor, the performance parameter failure factor and the safety parameter failure factor of each equipment unit is determined as the system-level failure factor of the equipment unit.

[0085] The present application also provides a coupled hydrogen production system fault detection device, comprising:

[0086] at least one processor; and,

[0087] a memory communicatively connected to the at least one processor; wherein,

[0088] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to implement the coupled hydrogen production system fault detection method recorded in any of the above embodiments.

[0089] The present application also provides a computer-readable storage medium. When the instructions in the storage medium are executed by a processor corresponding to the coupled hydrogen production system fault detection device, the coupled hydrogen production system fault detection device can implement the coupled hydrogen production system fault detection method recorded in any of the above embodiments.

[0090] Other features and advantages of the present application will be described in the following description, and partly become apparent from the description, or be understood by practicing the present application. The purpose and other advantages of the present application can be realized and obtained by the structures specifically pointed out in the written description, claims, and drawings.

[0091] The technical solution of the present application is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0092] The accompanying drawings are used to provide a further understanding of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings:

[0093] Figure 1 This is a flow chart of a coupled hydrogen production system fault detection method in one embodiment of the present application;

[0094] Figure 2 This is a schematic diagram of the structure of a coupled hydrogen production system in one embodiment of the present application;

[0095] Figure 3 A schematic diagram of the calculation logic of equipment performance fault detection index in one embodiment of the present application;

[0096] Figure 4 A fully connected network diagram of the variables associated with the coupled hydrogen production system is implemented for the first application;

[0097] Figure 5 This is a structural schematic diagram of a coupled hydrogen production system fault detection device in one embodiment of the present application;

[0098] Figure 6 This is a schematic diagram of the hardware structure of a coupled hydrogen production system fault detection device in one embodiment of the present application. DETAILED DESCRIPTION

[0099] The preferred embodiments of the present application are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present application and are not used to limit the present application.

[0100] Figure 1 Flow chart of a coupled hydrogen production system fault detection method in one embodiment of the present application, as shown in FIG. Figure 1 As shown, the method can be implemented as the following steps S101-S103:

[0101] In step S101, the monitoring values ​​of the preset parameters of each group of equipment units in the coupled hydrogen production system are obtained;

[0102] In step S102, a fault index of the coupled hydrogen production system is determined according to the monitoring values ​​of the preset parameters of each group of equipment units;

[0103] In step S103, when the fault index of the coupled hydrogen production system is greater than a first preset threshold, a fault warning message is sent to a preset terminal.

[0104] A coupled hydrogen production system is a system that combines a variety of different hydrogen production technologies to improve hydrogen production efficiency and comprehensive energy utilization. A coupled hydrogen production system can use multiple energy sources and technologies to produce hydrogen at the same time. Figure 2 Schematic diagram of the structure of a coupled hydrogen production system in one embodiment of the present application. Figure 2 As shown, the coupled hydrogen production system includes a power supply system and multiple groups of hydrogen production equipment units, and each group of hydrogen production equipment units includes an electrical conversion device, an electrolyzer, a purification device and a gas-liquid separation device.

[0105] In the present application, first, the monitoring values ​​of the preset parameters of each group of equipment units in the coupled hydrogen production system are obtained; specifically, the production capacity parameters, operating parameters, safety parameters, power supply fluctuation parameters and hydrogen production demand of each group of equipment units in the coupled hydrogen production system are collected.

[0106] Among them, as shown in Table 1, the parameter table of each equipment unit collection, the production capacity parameters of each group of equipment units include the hydrogen production and hydrogen purity corresponding to the equipment unit; the operating parameters include the current and voltage of the electrical conversion device, the voltage, current, pressure, and temperature of the electrolyzer, the operating power, pressure, flow rate and hydrogen purity of the purification device, and the operating power, pressure, flow rate and hydrogen purity of the gas-liquid separation device; the safety parameters include the content of hydrogen in oxygen HTO and oxygen in hydrogen OTH; the power supply volatility parameters include the current and voltage of the photovoltaic power generation system and the power of the wind power system; the hydrogen production demand includes the hydrogen production and hydrogen purity set according to the demand.

[0107] Table 1 Collection parameters of each equipment unit

[0108]

[0109]

[0110] Then, determining the fault index of the coupled hydrogen production system according to the monitoring values ​​of the preset parameters of each group of equipment units;

[0111] 1. Input the monitoring values ​​of the preset parameters of each group of equipment units into the preset model to obtain the fault indicator matrix of the coupled hydrogen production system. The fault indicator matrix at least includes the equipment performance fault factor, equipment safety fault factor, system-level fault factor and coupling fault factor of each group of equipment units;

[0112] Specifically, four fault factors corresponding to each group of equipment units are obtained according to the operating parameters (including equipment performance fault factor l1, equipment safety fault factor l2, system-level fault factor l3, coupling fault factor l4, and then the fault factors of multiple groups of equipment units can obtain the fault factor matrix L of the coupled hydrogen production system;

[0113] (1) Determination process of equipment performance failure factor l1:

[0114] ① Obtain the production capacity parameters and operating parameters of each group of equipment units.

[0115] ② Input the operating parameters into the first sub-model of the preset model to obtain the first predicted value of the capacity parameters of each group of equipment units. The first sub-model is a nonlinear model obtained based on the historical hydrogen capacity parameters and the historical equipment unit operating parameters. The following formula is the function expression of the first sub-model:

[0116]

[0117] in, is the first predicted value vector of the capacity parameter, NL1 is the nonlinear model, is the operating parameter vector of the electrolyzer; is the operating parameter vector of the electrical conversion device; is the operating parameter vector of the purification device; is the operating parameter vector of the gas-liquid separation device.

[0118] The nonlinear model NL1 may be a neural network or other nonlinear models, and this application does not make any specific limitation on this.

[0119] ③ Calculate the difference between the capacity parameter of each group of equipment units and the corresponding first predicted value as the first difference, and compare the first difference with the pre-set third preset threshold Δ1, wherein the third preset threshold can be determined by historical data statistical analysis (such as the 6σ method) or experience, and is an empirical parameter. If:

[0120]

[0121] Real-time production and hydrogen purity data of the equipment, It is the prediction result of nonlinear model NL1, namely the predicted output and hydrogen purity.

[0122] Then the first difference is used as the equipment performance failure factor:

[0123]

[0124] Among them, l1 is the equipment performance failure factor, The production capacity parameters collected in real time for the equipment, is the first predicted value vector of the capacity parameters.

[0125] like Figure 3 As shown in the figure, it is a logical diagram of the calculation of equipment performance fault detection indicators. The actual situation is a high-dimensional hyperplane space. Here, for the convenience of plane graphical display, it is assumed that the input parameter is 1-dimensional (for example, the input parameter is assumed to be: voltage, and the actual process is multi-dimensional input: voltage, current, pressure, temperature, etc.), and the output is also 1-dimensional (assuming: output). Figure 3The middle dots are the actual collected data, which are scattered in the two-dimensional plane space. Assume that the upper left dotted line is the theoretical curve of the relationship between input parameters and output obtained by modeling historical data through the NL1 nonlinear model (such as a neural network). Set the difference threshold Δ1, that is, the lower right threshold curve. If the real-time data is above the threshold curve (determined by calculating whether the distance from the data point to the upper left theoretical curve is less than the threshold Δ1), it is determined that the current equipment performance meets the requirements; if it is below the threshold curve, it means that the hydrogen production and quality have produced a serious degradation deviation, which does not meet the performance requirements, and it is determined to be a fault state. The lower the data output value and the farther it is from the theoretical curve, the more serious the fault problem. Therefore, the calculated distance, that is, the model residual value l1, represents the severity of the equipment-level performance failure problem:

[0126]

[0127] In addition, since it is necessary to construct a fault factor matrix in the future and unify the fault data of different dimensions for matrix calculation, it is necessary to normalize the fault data of different dimensions so that the parameter l1∈[0,1], norm() is the normalization calculation formula:

[0128]

[0129] If the following equation is satisfied,

[0130]

[0131] Then l1=0, indicating that there is no fault problem.

[0132] (2) Determination process of equipment safety failure factor l2:

[0133] ① Obtain the operating parameters and safety parameters of each group of equipment units;

[0134] ② Input the operating parameters into the second sub-model of the preset model to obtain the second predicted value of the safety parameter of each group of equipment units. The second sub-model is a nonlinear model trained based on historical data. The following formula is the function expression of the second sub-model:

[0135]

[0136] in, is the second predicted value of the safety parameter of each group of equipment units, NL2 is the nonlinear model, press is the pressure value of the electrolytic cell; temp is the temperature value of the electrolytic cell.

[0137] ③ Calculate the difference between the safety parameter of each group of equipment units and the second predicted value as the second difference, and compare the second difference with the fourth preset threshold Δ2. If (norm(S realtime)-norm(S pred ))≥Δ2, the normalized second difference is used as the equipment safety failure factor l2 to characterize the severity of the equipment safety failure problem:

[0138]

[0139] Among them, l2 is the equipment safety failure factor, It is the security parameters collected by the equipment in real time. It is the second predicted value of the safety parameter of each group of equipment units.

[0140] like l2=0.

[0141] (3) Determination process of system-level failure factor l3:

[0142] ① Obtain the production capacity parameters, performance parameters, safety parameters, power supply fluctuation parameters and hydrogen production requirements of each group of equipment units;

[0143] ② Input the power supply volatility parameters and hydrogen production demand into the third sub-model of the preset model to obtain the predicted values ​​of the production capacity parameters, performance parameters and safety parameters of each group of equipment units.

[0144] The third sub-model of the preset model is a nonlinear relationship model obtained by training based on historical data. Since the new energy power supply has the characteristic of strong volatility, and the coupled hydrogen production system expects to effectively absorb power fluctuations through the optimized combination of hydrogen production equipment arrays with multiple different technical routes, it is necessary to set a calculation method for the performance index of fluctuating power supply absorption. In this application, the third sub-model of the preset model includes the corresponding mean μ and variance σ for the power supply volatility parameter and the hydrogen production demand volatility parameter, that is, the mean and variance of the voltage volatility parameter and the hydrogen production demand parameter are calculated according to the measured values, and then the obtained mean and variance are used as the input variables of the model. The following formula is the function expression of the third sub-model of the preset model:

[0145]

[0146] Among them, NL3 is a nonlinear model; is the mean vector of power supply volatility parameters and hydrogen production demand volatility parameters; is the variance vector of power supply volatility parameter and hydrogen production demand volatility parameter; is the third predicted value.

[0147] further, in, is the third predicted value of the hydrogen production capacity parameter; is the third predicted value of the performance parameter; is the third predicted value of the safety parameter.

[0148] ③ Calculate the difference between the capacity parameter, performance parameter and safety parameter of each group of equipment units and the corresponding predicted value, and compare them with the corresponding pre-set threshold Δ 3i For comparison:

[0149] if The difference is taken as the fault factor l of the corresponding parameter 3i :

[0150]

[0151] like l 3i =0

[0152] Among them, l 3i is the fault factor corresponding to each parameter, is the third predicted value of each parameter, is the real-time acquisition parameter of each parameter, i=(1,2,3).

[0153] ④ Further, the sum of the failure factors corresponding to the capacity parameters, performance parameters and safety parameters is taken as the system-level failure factor l3, that is:

[0154]

[0155] Furthermore, through the hydrogen production system for new energy power input, we can consider the equipment failure problem from the system level. For example, the fluctuating power input may affect the equipment, so the ability to absorb the fluctuation of new energy is an important indicator to consider whether the equipment is abnormal. In other words, although the operating parameters of the equipment itself are not abnormal, the decline in the ability to absorb the fluctuating power supply (that is, the hydrogen production level of the equipment is reduced compared with the same historical fluctuations) is also one of the failure situations.

[0156] (4) Determination process of coupling fault factor l4:

[0157] ① Construct different arrangements and combinations of electrical conversion devices, electrolyzers, purification devices, and gas-liquid separation devices to form a fully connected network structure set of coupled hydrogen production systems.

[0158] Figure 4 For the first application, a fully connected network diagram of the variable association of the coupled hydrogen production system is implemented, such as Figure 4 As shown in the figure, considering the cluster coupling characteristics of the coupled hydrogen production system, when some devices fail, the system can still be reconstructed by matching different hydrogen production arrays and upstream and downstream electrical conversion devices, purification devices and gas-liquid separation devices to keep the overall system running. At this time, the performance curve of the individual hydrogen production device will be offset compared to the steady-state operation. Therefore, the following is established: Figure 4 The fully connected graph network structure shown in Figure 2 is shown in Figure 2. Figure 4 As shown, the electrical conversion device as an upstream device is the guarantee of the operation of the electrolyzer. The operating state of the electrical conversion device directly affects the performance of the electrolyzer connected downstream. Therefore, the electrical conversion device serves as the parent node (i.e., the cause node) of the electrolyzer. At the same time, the operation of the downstream purification device and the gas-liquid separation device depends on the operation of the electrolyzer. Therefore, the purification and gas-liquid separation devices serve as the child nodes (result nodes) of the electrolyzer. Considering that when some equipment fails, any reconstruction of the system connection may be performed, a fully connected structure of all electrical conversion devices, electrolyzers, purification and gas-liquid separation devices is established to ensure adaptability after reconstruction. However, under normal circumstances, each electrolyzer device is connected to a certain electrical conversion device, purification and gas-liquid separation device in the coupled hydrogen production system, and the connection will not be changed when no failure occurs. Therefore, although the network structure is fully connected, only some of the connections have data in actual operation, and most of the data is 0, so it belongs to sparse calculation. This application uses a Bayesian network structure to infer the result by probability calculation. The data 0 can be replaced by a smoothing factor (a smaller value, such as e -3 ) effectively handles the sparsity problem without causing the probability inference calculation to diverge.

[0159] ② Determine the predicted value of the performance indicator parameter vector of each equipment unit based on the current operating data.

[0160] By maximizing the Bayesian posterior estimate, that is, by probability calculation, the possibility of the actual operation data occurring is maximized. On the premise of obtaining the actual operation data, for each combination of connection structures, the corresponding Bayesian network posterior probability can be calculated:

[0161]

[0162] Among them, p(x) is the probability of different connection structures, x k is the parameter of node k, pa k is the parameter of the parent node corresponding to node k.

[0163] argmax is a function that finds the parameter of a function and returns the monitoring value when the function reaches the maximum value. Figure 4 The fully connected structure of the device can obtain the predicted value of the performance indicator parameter vector of the device through the argmax function and maximizing the Bayesian posterior estimation:

[0164]

[0165] in, The result obtained by Bayesian posterior estimation of the hydrogen production corresponding to a certain equipment unit, that is, the predicted value of the performance indicator parameter vector of the equipment; is the parameter vector of the electrical conversion device, is the parameter vector of the purification device, is the parameter vector of the gas-liquid separation device, and x is the hydrogen production of the equipment.

[0166] ③ Determine the coupling fault factor l4:

[0167] Set the yield difference threshold Δ4 if:

[0168]

[0169] Output l4 is used to characterize the severity of performance failure of the equipment unit in the coupled cluster system:

[0170]

[0171] if:

[0172] (norm(prod pred )-norm(prod realtime ))<Δ4

[0173] Output l4=0, indicating that there is no fault problem.

[0174] After obtaining the fault factors of the four dimensions of l1, l2, l3, and l4 of each group of equipment units, the calculation results are combined into a row in the fault factor matrix, and the fault factors of each group of equipment units in the coupled hydrogen production system are calculated in turn, and the final results are combined into the fault factor matrix L:

[0175]

[0176] Among them, l ij (i=1,2,……,n,j=1,2,3,4) is the jth failure factor of the ith equipment unit.

[0177] 2. After obtaining the fault index matrix, multiply the fault index matrix of the coupled hydrogen production system and the fault factor weight to obtain the fault degree vector of the coupled hydrogen production system; the fault factor matrix L and the fault factor weight are multiplied as follows: Multiply to get the fault severity vector The fault degree vector is calculated by the following formula:

[0178]

[0179] Specifically, under the steady-state operation conditions of the system, the weights of the four fault factors can be pre-set, for example, w1, w2, w3, and w4 are set to 0.8, 2, 1.5, and 0 respectively; among them, since the safety index of the hydrogen production process is the most important consideration, w2 is set to the highest weight 2. Since the value range of all parameters is [0,1], the system is twice as sensitive to the safety fault index parameter as other fault indicators. Since the coupled hydrogen production system can still guarantee the operation of the system to a certain extent by reconstructing the connection after some equipment fails, the performance failure impact in the steady state is relatively small, and the set l1 weight w1 is 0.8. The ability of the coupled hydrogen production system to absorb fluctuating power sources is its outstanding advantage, so the weight w3 of the system-level performance fault factor l3 has a relatively high weight, which is set to 1.5. Since l4 is the fault characterization indicator after the system is reconstructed after some equipment fails, its weight is set to 0 under the originally designed steady-state connection; when some equipment in the system fails, the cluster operation mode is adjusted and the weights w1, w2, w3, and w4 are updated to 0, 2, 1.5, and 1. At this time, due to the failure of some equipment, the system is reconstructed and the connection mode of the upstream and downstream equipment is different from the original steady state. Therefore, l4 is needed to update w4 to 1 and change the weight w1 of the device-level failure factor representing the original steady state to 0; when the system is put into operation, the weight parameters are fine-tuned by analyzing the collected data. The data includes: failure frequency, operation and maintenance cost curve, and operation and maintenance cycle cost data.

[0180] 3. Multiply the weight of each group of equipment units by the fault degree vector of the coupled hydrogen production system to obtain the fault index of the coupled hydrogen production system. Specifically, as shown in the following formula, the weight of each equipment unit is multiplied by the fault degree vector of the coupled hydrogen production system to obtain the fault index of the coupled hydrogen production system. and the fault severity vector After multiplication, the fault index F of the coupled hydrogen production system is obtained. The fault index is calculated by the following formula:

[0181]

[0182] The weight of each equipment unit is set according to the role played by each group of equipment units (including electrolytic cell device, electrical conversion device, purification and gas-liquid separation device) in the system. When setting weights, you can evaluate the safety level, reliability, maintenance difficulty, and operating efficiency. Each evaluation dimension can be scored from 1 to 10. The lower the safety level, reliability, and operating efficiency, the higher the score. The higher the maintenance difficulty, the higher the score. You can set the score of each device based on experience. After the fault detection system is put into operation, adjust the evaluation score by collecting historical data, including the historical failure frequency of the equipment, the slope of the efficiency drop fitting curve, maintenance cost and cycle, etc. Finally, the weight parameter of the equipment is obtained by normalizing the indicators of all dimensions. And calculate the final fault index F.

[0183] Finally, when the fault index of the coupled hydrogen production system is greater than the first preset threshold, a fault warning message is sent to the preset terminal. Specifically, if F is greater than the set system fault warning threshold, a fault warning is output. The warning threshold is an empirical value obtained based on historical data.

[0184] In addition, since the fault degree vector of the coupled hydrogen production system The factors are used to characterize the fault degree of each equipment unit. Find the first m equipment units with the highest values ​​and locate the problematic equipment units; of course, they can also be compared with the preset fault severity threshold to determine that the equipment units with values ​​greater than the preset threshold are faulty equipment units; and determine the level of equipment failure for the first m equipment units based on the four failure indicators, that is, determine whether it belongs to equipment performance, equipment safety, system-level failure, or coupling-level failure).

[0185] In addition, in this application, the fault indicator vector Take the reciprocal of each element in Among them, when f i = 0, take h i = 1. Set the h of each device unit i , multiplied by the corresponding device weight e i , get the health assessment index H of the equipment i =h i ×e i , which is used to evaluate the health status of each equipment unit. Finally, the health evaluation index of each equipment unit is an important basis for the power load allocation of the coupled hydrogen production system.

[0186] In addition, according to Figure 4 This application also proposes a dynamic adaptive fault detection method, which has good cluster dynamic applicability and a wide range of application modes:

[0187] 1) The method proposed in the present invention fully considers the cluster coupling characteristics of the coupled hydrogen production system. When some equipment in the coupled hydrogen production system fails, the overall system can still be operated continuously by matching different hydrogen production arrays and upstream and downstream electrical conversion devices, purification devices and gas-liquid separation devices. At this time, the performance curve of the individual hydrogen production equipment will be offset compared to the steady-state operation. By establishing a fully connected graph network structure of all hydrogen production equipment and electrical conversion equipment, purification devices and gas-liquid separation devices in the cluster, it is possible to predict the equipment performance failure state after the system is dynamically optimized and matched, and incorporate the state index into the equipment failure index matrix;

[0188] 2) When some equipment fails and the upstream and downstream equipment of the system reorganize and match the operation mode, the present invention proposes a method of switching the weight mode to update the fault indicator matrix to ensure the accuracy of judging and detecting the dynamic fault state of the system. The method of collecting data to fine-tune the weight can further improve the applicability;

[0189] The present invention proposes three coupled hydrogen production fault detection and health status assessment systems, which can be used as follows: Figure 2 Three different modes are shown: (a) providing faulty equipment information to operators, who then judge and manually handle the fault information based on their experience; (b) evaluating the health status of the equipment and pushing fault problems and health status information through an automatic system; (c) using the equipment health status and fault detection results as an important basis for the optimal scheduling of the coupled hydrogen production system, and directly participating in the feedback control of the coupled hydrogen production optimal scheduling.

[0190] The beneficial effects of the present application are: by obtaining the monitoring values ​​of the preset parameters of each group of equipment units in the coupled hydrogen production system; determining the fault index of the coupled hydrogen production system according to the monitoring values ​​of the preset parameters of each group of equipment units; when the fault index of the coupled hydrogen production system is greater than the first preset threshold, sending fault warning information to the preset terminal. Since the preset parameters of multiple groups of equipment units are collected, the coupled hydrogen production system of multiple groups of equipment units can be comprehensively detected for faults, rather than just monitoring the faults of a single device, so as to achieve comprehensive fault detection of the coupled hydrogen production system and improve detection efficiency and accuracy.

[0191] In one embodiment, the above step S102 may be implemented as the following steps A1-A3:

[0192] In step A1, the monitoring values ​​of the preset parameters of each group of equipment units are input into a preset model to obtain a fault indicator matrix of the coupled hydrogen production system, wherein the fault indicator matrix at least includes equipment performance failure factors, equipment safety failure factors, system-level failure factors and coupling failure factors of each group of equipment units;

[0193] In step A2, the fault index matrix of the coupled hydrogen production system and the fault factor weight are multiplied to obtain a fault degree vector of the coupled hydrogen production system;

[0194] In step A3, the weight of each group of equipment units is multiplied by the fault degree vector of the coupled hydrogen production system to obtain a fault index of the coupled hydrogen production system.

[0195] The beneficial effect of this embodiment is that the monitoring values ​​of the preset parameters of each group of equipment units are input into the preset model to obtain the equipment performance fault factor, equipment safety fault factor, system-level fault factor and coupling fault factor of the hydrogen production system, including the fault factor at the equipment level and the fault factor at the system level. Therefore, it not only detects faults at the level of a single equipment, but also includes fault detection at the system level. The accuracy of fault detection of the coupled hydrogen production system is improved.

[0196] In one embodiment, the above step S103 may be implemented as the following steps B1-B3:

[0197] In step B1, the elements in the fault degree vector are sorted from large to small according to the numerical values;

[0198] In step B2, it is determined that the equipment units corresponding to the first preset number of elements in the sequence are faulty equipment units;

[0199] In step B3, fault warning information including the identification of the faulty equipment unit is sent to a preset terminal.

[0200] The beneficial effect of this embodiment is that by sorting the elements in the fault degree vector, the fault degree of each equipment unit is determined, and then the faulty equipment unit is determined, and the faulty equipment unit identification is sent during the fault warning, without the need for manual investigation one by one, thereby improving the efficiency of fault detection.

[0201] In one embodiment, the above step S103 may also be implemented as the following steps B4-B6:

[0202] In step B4, the elements in the fault degree vector are respectively compared with the second preset threshold value;

[0203] In step B5, the device unit corresponding to the element in the fault degree vector that is greater than the second preset threshold is determined to be a faulty device unit;

[0204] In step B6, fault warning information including the faulty equipment unit identifier is sent to a preset terminal.

[0205] The beneficial effect of this embodiment is that by screening the devices with a fault degree vector greater than a preset threshold, the devices with a higher fault degree are determined to be faulty device units, and the faulty device unit identification is sent during fault warning, without the need for manual investigation one by one, thereby improving the efficiency of fault detection.

[0206] In one embodiment, the method can also be implemented as the following steps C1-C2:

[0207] In step C1, multiple failure factors of the faulty equipment unit are sorted from large to small according to numerical values;

[0208] In step C2, the fault factor with the largest value is determined as the fault cause of the faulty equipment unit;

[0209] The above step S103 can also be implemented as the following step C3:

[0210] In step C3, fault warning information including the fault cause is sent to a preset terminal.

[0211] The beneficial effect of this embodiment is that: by analyzing multiple fault factors of the faulty equipment unit, the fault cause of the faulty equipment is determined, and the fault cause is sent during the fault warning, thereby improving the efficiency of fault detection.

[0212] In one embodiment, the equipment performance failure factor can be determined by the following steps D1-D5:

[0213] In step D1, the monitoring values ​​of the production capacity parameters and operating parameters of each group of equipment units are obtained;

[0214] In step D2, the monitored values ​​of the operating parameters are input into the first sub-model of the preset model to obtain first predicted values ​​of the capacity parameters of each group of equipment units;

[0215] In step D3, the difference between the monitored value of the capacity parameter of each group of equipment units and the first predicted value is taken as the first difference;

[0216] In step D4, when there is a first equipment unit whose first difference is greater than or equal to the third preset threshold, determining that the equipment performance failure factor of the first equipment unit is the first difference;

[0217] In step D5, when there is a second equipment unit whose first difference is less than the third preset threshold, it is determined that the equipment performance failure factor of the second equipment unit is 0;

[0218] The equipment safety failure factor can be determined by the following steps E1-E5:

[0219] In step E1, the monitoring values ​​of the operating parameters and safety parameters of each group of equipment units are obtained;

[0220] In step E2, the monitored value of the operating parameter is input into the second sub-model of the preset model to obtain the second predicted value of the safety parameter of each group of equipment units;

[0221] In step E3, the difference between the monitored value of the safety parameter of each group of equipment units and the second predicted value is used as the second difference;

[0222] In step E4, when there is a third equipment unit whose second difference is greater than or equal to a fourth preset threshold, determining that the equipment safety failure factor of the third equipment unit is the second difference;

[0223] In step E5, when there is a fourth equipment unit whose second difference is smaller than a fourth preset threshold, it is determined that the equipment safety failure factor of the fourth equipment unit is 0.

[0224] In one embodiment, the system-level failure factor may be determined by the following steps F1-F4:

[0225] In step F1, the monitoring values ​​of the production capacity parameters, performance parameters, safety parameters, power supply fluctuation parameters and hydrogen production demand of each group of equipment units are obtained;

[0226] In step F2, the monitoring values ​​of the power supply volatility parameter and the hydrogen production demand are input into the third sub-model of the preset model to obtain the predicted values ​​of the production capacity parameter, the production capacity parameter and the safety parameter of each group of equipment units respectively;

[0227] In step F3, the difference between the monitored value and the predicted value of the capacity parameter, performance parameter and safety parameter of each equipment unit is compared with the corresponding preset threshold value to determine the capacity parameter failure factor, performance parameter failure factor and safety parameter failure factor of each equipment unit;

[0228] In step F4, the sum of the production capacity parameter failure factor, the performance parameter failure factor and the safety parameter failure factor of each equipment unit is determined as the system-level failure factor of the equipment unit.

[0229] In one embodiment, the system-level failure factor may be determined by the following steps G1-G7:

[0230] In step G1, the monitoring values ​​of the production capacity parameters, performance parameters, safety parameters, power supply fluctuation parameters and hydrogen production demand of each group of equipment units are obtained;

[0231] In step G2, the monitoring values ​​of the power supply volatility parameter and the hydrogen production demand are input into the third sub-model of the preset model, and the third predicted value of the capacity parameter of each group of equipment units, the fourth predicted value of the performance parameter of the capacity parameter of each group of equipment units and the fifth predicted value of the safety parameter of each group of equipment units are obtained respectively;

[0232] In step G3, the difference between the capacity parameter of each group of equipment units and the corresponding third predicted value is determined to be a third difference, the difference between the performance parameter of each group of equipment units and the corresponding fourth predicted value is determined to be a fourth difference, and the difference between the safety parameter of each group of equipment units and the corresponding fifth predicted value is determined to be a fifth difference;

[0233] In step G4, when there is a target device unit whose third difference is greater than or equal to the capacity threshold, the failure factor of the capacity parameter of the target device unit is determined to be the third difference; when there is a target device unit whose third difference is less than the capacity threshold, the failure factor of the capacity parameter of the target device unit is determined to be 0;

[0234] In step G5, when there is a target device unit whose fourth difference is greater than or equal to the performance threshold, the failure factor of the performance parameter of the target device unit is determined to be the fourth difference; when there is a target device unit whose fourth difference is less than the performance threshold, the failure factor of the performance parameter of the target device unit is determined to be 0;

[0235] In step G6, when there is a target device unit whose fifth difference is greater than or equal to the capacity threshold, the failure factor of the safety parameter of the target device unit is determined to be the fifth difference; when there is a target device unit whose fifth difference is less than the safety threshold, the failure factor of the safety parameter of the target device unit is determined to be 0;

[0236] In step G7, the sum of the production capacity parameter failure factor, the performance parameter failure factor and the safety parameter failure factor of each equipment unit is determined as the system-level failure factor of the equipment unit.

[0237] Figure 5 FIG. 1 is a schematic diagram of a coupled hydrogen production system fault detection device according to an embodiment of the present application. Figure 5 As shown, the device comprises:

[0238] The acquisition module 501 is used to acquire the monitoring values ​​of the preset parameters of each group of equipment units in the coupled hydrogen production system;

[0239] A first determination module 502, configured to determine a fault index of the coupled hydrogen production system according to monitoring values ​​of preset parameters of each group of equipment units;

[0240] The sending module 503 is used to send fault warning information to a preset terminal when the fault index of the coupled hydrogen production system is greater than a first preset threshold.

[0241] In one embodiment, the determining module includes:

[0242] An input submodule, used to input the monitoring values ​​of the preset parameters of each group of equipment units into a preset model to obtain a fault indicator matrix of the coupled hydrogen production system, wherein the fault indicator matrix at least includes equipment performance failure factors, equipment safety failure factors, system-level failure factors and coupling failure factors of each group of equipment units;

[0243] A first multiplication submodule is used to multiply the fault index matrix of the coupled hydrogen production system and the fault factor weight to obtain a fault degree vector of the coupled hydrogen production system;

[0244] The second multiplication submodule is used to multiply the weight of each group of equipment units by the fault degree vector of the coupled hydrogen production system to obtain a fault index of the coupled hydrogen production system.

[0245] In one embodiment, the sending module includes:

[0246] A first sorting submodule, used to sort the elements in the fault degree vector from large to small according to numerical values;

[0247] A first determination submodule, configured to determine that the equipment units corresponding to the first preset number of elements in the sequence are faulty equipment units;

[0248] The first sending submodule is used to send fault warning information including the faulty equipment unit identifier to a preset terminal.

[0249] In one embodiment, the sending module includes:

[0250] A comparison submodule, used for comparing the elements in the fault degree vector with the second preset threshold value respectively;

[0251] A second determination submodule, configured to determine that a device unit corresponding to an element in the fault degree vector that is greater than a second preset threshold value is a faulty device unit;

[0252] The second sending submodule is used to send the fault warning information including the faulty equipment unit identifier to a preset terminal.

[0253] In one embodiment, the apparatus further comprises:

[0254] A sorting module, used to sort the multiple fault factors of the faulty equipment unit from large to small according to numerical values;

[0255] A second determination module is used to determine the fault factor with the largest value as the fault cause of the faulty equipment unit;

[0256] The sending module is further used for:

[0257] Sending fault warning information including the fault cause to a preset terminal.

[0258] In one embodiment, the device performance failure factor is determined by:

[0259] Obtain monitoring values ​​of production capacity parameters and operating parameters of each group of equipment units;

[0260] Inputting the monitored values ​​of the operating parameters into the first sub-model of the preset model to obtain first predicted values ​​of the production capacity parameters of each group of equipment units;

[0261] The difference between the monitored value of the capacity parameter of each group of equipment units and the first predicted value is taken as the first difference;

[0262] When there is a first equipment unit whose first difference is greater than or equal to a third preset threshold, determining that the equipment performance failure factor of the first equipment unit is the first difference;

[0263] When there is a second equipment unit whose first difference is less than a third preset threshold, determining that the equipment performance failure factor of the second equipment unit is 0;

[0264] The equipment safety failure factor is determined in the following manner:

[0265] Obtain monitoring values ​​of operating parameters and safety parameters of each group of equipment units;

[0266] Inputting the monitored value of the operating parameter into the second sub-model of the preset model to obtain the second predicted value of the safety parameter of each group of equipment units;

[0267] The difference between the monitored value of the safety parameter of each group of equipment units and the second predicted value is used as the second difference;

[0268] When there is a third equipment unit whose second difference is greater than or equal to a fourth preset threshold, determining that the equipment safety failure factor of the third equipment unit is the second difference;

[0269] When there is a fourth equipment unit whose second difference is less than a fourth preset threshold, it is determined that the equipment safety failure factor of the fourth equipment unit is 0.

[0270] In one embodiment, the system-level failure factor is determined by:

[0271] Obtain monitoring values ​​of production capacity parameters, performance parameters, safety parameters, power supply fluctuation parameters and hydrogen production demand of each group of equipment units;

[0272] Inputting the monitoring values ​​of the power supply volatility parameter and the hydrogen production demand into the third sub-model of the preset model, respectively obtaining the predicted values ​​of the production capacity parameter, the production capacity parameter and the safety parameter of each group of equipment units;

[0273] The difference between the monitored value and the predicted value of the capacity parameter, performance parameter and safety parameter of each equipment unit is compared with the corresponding preset threshold value to determine the capacity parameter failure factor, performance parameter failure factor and safety parameter failure factor of each equipment unit;

[0274] The sum of the production capacity parameter failure factor, the performance parameter failure factor and the safety parameter failure factor of each equipment unit is determined as the system-level failure factor of the equipment unit.

[0275] Figure 6 FIG. 1 is a schematic diagram of the hardware structure of a coupled hydrogen production system fault detection device in one embodiment of the present application. Figure 6 As shown, the coupled hydrogen production system fault detection device comprises:

[0276] at least one processor 620; and,

[0277] A memory 604 in communication with the at least one processor 620; wherein,

[0278] The memory 604 stores instructions that can be executed by the at least one processor 620, and the instructions are executed by the at least one processor 620 to implement the coupled hydrogen production system fault detection method described in any of the above embodiments.

[0279] Reference Figure 6 The coupled hydrogen production system fault detection device 600 may include one or more of the following components: a processing component 602, a memory 604, a power component 606, a multimedia component 608, an audio component 610, an input / output (I / O) interface 612, a sensor component 614, and a communication component 616.

[0280] The processing component 602 generally controls the overall operation of the coupled hydrogen production system fault detection device 600. The processing component 602 may include one or more processors 620 to execute instructions to complete all or part of the steps of the above method. In addition, the processing component 602 may include one or more modules to facilitate the interaction between the processing component 602 and other components. For example, the processing component 602 may include a multimedia module to facilitate the interaction between the multimedia component 608 and the processing component 602.

[0281] The memory 604 is configured to store various types of data to support the operation of the coupled hydrogen production system fault detection device 600. Examples of such data include instructions for any application or method operating on the coupled hydrogen production system fault detection device 600, such as text, pictures, videos, etc. The memory 604 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0282] The power supply assembly 606 provides power to various components of the coupled hydrogen production system fault detection device 600. The power supply assembly 606 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the onboard control system 600.

[0283] The multimedia component 608 includes a screen that provides an output interface between the coupled hydrogen production system fault detection device 600 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor can not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 608 may also include a front camera and / or a rear camera. When the coupled hydrogen production system fault detection device 600 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera can receive external multimedia data. Each front camera and rear camera can be a fixed optical lens system or have focal length and optical zoom capabilities.

[0284] The audio component 610 is configured to output and / or input audio signals. For example, the audio component 610 includes a microphone (MIC), and when the coupled hydrogen production system fault detection device 600 is in an operation mode, such as an alarm mode, a recording mode, a voice recognition mode, and a voice output mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 604 or sent via the communication component 616. In some embodiments, the audio component 610 also includes a speaker for outputting an audio signal.

[0285] I / O interface 612 provides an interface between processing component 602 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.

[0286] The sensor assembly 614 includes one or more sensors for providing various aspects of status assessment for the coupled hydrogen production system fault detection device 600. For example, the sensor assembly 614 may include a sound sensor. In addition, the sensor assembly 614 may detect the open / closed state of the coupled hydrogen production system fault detection device 600, the relative positioning of the components, such as the display and keypad of the coupled hydrogen production system fault detection device 600, and the sensor assembly 614 may also detect the operating state of the coupled hydrogen production system fault detection device 600 or a component of the coupled hydrogen production system fault detection device 600, such as the operating state of the air distribution plate, the structural state, the operating state of the discharge scraper, etc., the orientation or acceleration / deceleration of the coupled hydrogen production system fault detection device 600 and the temperature change of the coupled hydrogen production system fault detection device 600. The sensor assembly 614 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 614 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 614 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, a material stack thickness sensor, or a temperature sensor.

[0287] The communication component 616 is configured to enable the coupled hydrogen production system fault detection device 600 to provide the ability to communicate with other devices and cloud platforms in a wired or wireless manner. The coupled hydrogen production system fault detection device 600 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 616 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 616 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0288] In an exemplary embodiment, the coupled hydrogen production system fault detection device 600 can be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to execute the coupled hydrogen production system fault detection method described in any of the above embodiments.

[0289] The present application also provides a computer-readable storage medium. When the instructions in the storage medium are executed by a processor corresponding to the coupled hydrogen production system fault detection device, the coupled hydrogen production system fault detection device can implement the coupled hydrogen production system fault detection method recorded in any of the above embodiments.

[0290] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) that contain computer-usable program code.

[0291] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0292] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0293] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0294] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A coupled hydrogen production system fault detection method, characterized in that: include: Obtaining monitoring values ​​of preset parameters of each group of equipment units in the coupled hydrogen production system; Determining a fault index of the coupled hydrogen production system according to monitoring values ​​of preset parameters of each group of equipment units; When the fault index of the coupled hydrogen production system is greater than a first preset threshold, a fault warning message is sent to a preset terminal.

2. The method according to claim 1, characterized in that Determining the fault index of the coupled hydrogen production system according to the monitoring values ​​of the preset parameters of each group of equipment units includes: Inputting the monitoring values ​​of the preset parameters of each group of equipment units into a preset model to obtain a fault indicator matrix of the coupled hydrogen production system, wherein the fault indicator matrix at least includes equipment performance failure factors, equipment safety failure factors, system-level failure factors and coupling failure factors of each group of equipment units; Multiplying the fault index matrix of the coupled hydrogen production system and the fault factor weight to obtain a fault degree vector of the coupled hydrogen production system; The weight of each group of equipment units is multiplied by the fault degree vector of the coupled hydrogen production system to obtain a fault index of the coupled hydrogen production system.

3. The method according to claim 2, characterized in that The sending of fault warning information to a preset terminal includes: Sort the elements in the fault degree vector from large to small according to their values; Determining that the equipment units corresponding to the first preset number of elements in the sorting are faulty equipment units; Sending fault warning information including the faulty equipment unit identifier to a preset terminal.

4. The method according to claim 2, characterized in that The sending of fault warning information to a preset terminal includes: Comparing the elements in the fault degree vector with the second preset threshold value respectively; Determine that the device unit corresponding to the element in the fault degree vector that is greater than a second preset threshold is a faulty device unit; Sending fault warning information including the faulty equipment unit identifier to a preset terminal.

5. The method according to claim 3 or 4, characterized in that The method further comprises: Sorting the multiple failure factors of the failed equipment unit from large to small according to the numerical values; Determine the fault factor with the largest value as the fault cause of the faulty equipment unit; The sending of fault warning information to a preset terminal also includes: Sending fault warning information including the fault cause to a preset terminal.

6. The method according to claim 2, characterized in that The equipment performance failure factor is determined as follows: Obtain monitoring values ​​of production capacity parameters and operating parameters of each group of equipment units; Inputting the monitored values ​​of the operating parameters into the first sub-model of the preset model to obtain first predicted values ​​of the production capacity parameters of each group of equipment units; The difference between the monitored value of the capacity parameter of each group of equipment units and the first predicted value is taken as the first difference; When there is a first equipment unit whose first difference is greater than or equal to a third preset threshold, determining that the equipment performance failure factor of the first equipment unit is the first difference; When there is a second equipment unit whose first difference is less than a third preset threshold, determining that the equipment performance failure factor of the second equipment unit is 0; The equipment safety failure factor is determined in the following manner: Obtain monitoring values ​​of operating parameters and safety parameters of each group of equipment units; Inputting the monitored value of the operating parameter into the second sub-model of the preset model to obtain the second predicted value of the safety parameter of each group of equipment units; The difference between the monitored value of the safety parameter of each group of equipment units and the second predicted value is used as the second difference; When there is a third equipment unit whose second difference is greater than or equal to a fourth preset threshold, determining that the equipment safety failure factor of the third equipment unit is the second difference; When there is a fourth equipment unit whose second difference is less than a fourth preset threshold, it is determined that the equipment safety failure factor of the fourth equipment unit is 0.

7. The method according to claim 2, characterized in that The system-level failure factor is determined as follows: Obtain monitoring values ​​of production capacity parameters, performance parameters, safety parameters, power supply fluctuation parameters and hydrogen production demand of each group of equipment units; Inputting the monitoring values ​​of the power supply volatility parameter and the hydrogen production demand into the third sub-model of the preset model, respectively obtaining the predicted values ​​of the production capacity parameter, the production capacity parameter and the safety parameter of each group of equipment units; The difference between the monitored value and the predicted value of the capacity parameter, performance parameter and safety parameter of each equipment unit is compared with the corresponding preset threshold value to determine the capacity parameter failure factor, performance parameter failure factor and safety parameter failure factor of each equipment unit; The sum of the production capacity parameter failure factor, the performance parameter failure factor and the safety parameter failure factor of each equipment unit is determined as the system-level failure factor of the equipment unit.

8. A coupled hydrogen production system fault detection device, characterized in that: include: An acquisition module, used to acquire monitoring values ​​of preset parameters of each group of equipment units in the coupled hydrogen production system; A first determination module, configured to determine a fault index of the coupled hydrogen production system according to monitoring values ​​of preset parameters of each group of equipment units; The sending module is used to send fault warning information to a preset terminal when the fault index of the coupled hydrogen production system is greater than a first preset threshold.

9. A coupled hydrogen production system fault detection device, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to implement the coupled hydrogen production system fault detection method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: When the instructions in the storage medium are executed by a processor corresponding to the coupled hydrogen production system fault detection device, the coupled hydrogen production system fault detection device can implement the coupled hydrogen production system fault detection method as described in any one of claims 1-7.

Images