Intelligent explosion-proof pressure relief hydrogen storage cylinder and control method thereof

Abstract

The application discloses an intelligent explosion-proof pressure relief hydrogen storage cylinder and a control method thereof, and relates to the technical field of container pressure relief.The hydrogen storage cylinder discloses a hydrogen storage cylinder body, an intelligent control unit, a multi-stage pressure relief system and a data acquisition system.Through a multi-stage pressure relief scheme, the pressure can be accurately adjusted, and the pressure relief process is stable and controllable.Combining an LSTM model and the correlation and influence between the internal pressure, the internal temperature and the medium flow in the hydrogen storage cylinder, the subsequent pressure of the hydrogen storage cylinder can be accurately and comprehensively predicted, and the corresponding pressure relief scheme can be dynamically adopted for pressure relief adjustment, so that the hydrogen storage cylinder can be reasonably and effectively pressure relieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of container pressure relief, more particularly, it relates to an intelligent explosion-proof pressure relief hydrogen storage cylinder and a control method thereof. BACKGROUND

[0002] With the continuous expansion of industrial production scale, hydrogen storage cylinders are increasingly widely used in chemical industry, petroleum, energy and other industries. There is an overpressure explosion risk in the operation of hydrogen storage cylinders. How to realize intelligent and precise explosion-proof pressure relief control has become a key problem to ensure the safe operation of hydrogen storage cylinders.

[0003] At present, the conventional hydrogen storage cylinder pressure relief device mostly uses a mechanical safety valve. This method has the following disadvantages: first, the pressure relief starting pressure is fixed and cannot be adjusted in real time according to the working conditions; second, the pressure relief amount is uncontrollable, which easily causes medium waste; third, there is a lack of intelligent early warning mechanism, and the pressure relief is often triggered when the pressure reaches the critical value, which has a certain hysteresis; fourth, the single pressure relief mode is difficult to cope with complex and variable working conditions, and there are safety hazards. SUMMARY

[0004] In view of the deficiencies in the prior art, the purpose of the present application is to provide an intelligent explosion-proof pressure relief hydrogen storage cylinder and a control method thereof.

[0005] To achieve the above-mentioned purpose, the present application provides the following technical solutions:

[0006] An intelligent explosion-proof pressure relief hydrogen storage cylinder, comprising a hydrogen storage cylinder body, an intelligent control unit, a multi-stage pressure relief system and a data acquisition system;

[0007] The intelligent control unit is electrically connected with the hydrogen storage cylinder body;

[0008] The intelligent control unit periodically acquires the predicted pressure of the hydrogen storage cylinder, determines whether to start the pressure relief warning based on the comparison result of the predicted pressure and the predicted reference pressure, and determines to start the emergency pressure relief valve pressure relief, the secondary pressure relief valve pressure relief or the primary pressure relief valve pressure relief after starting the pressure relief warning;

[0009] The multi-stage pressure relief system is fixed on the hydrogen storage cylinder body;

[0010] The data acquisition system is used to acquire the internal pressure, internal temperature and medium flow of the hydrogen storage cylinder.

[0011] Further, the multi-stage pressure relief system comprises a primary pressure relief valve, a secondary pressure relief valve and an emergency pressure relief valve arranged in series, all of which are electrically connected with the intelligent control unit.

[0012] Further, the primary pressure relief valve adopts an electric regulating valve structure; the secondary pressure relief valve adopts an electromagnetic quick opening and closing valve structure; and the emergency pressure relief valve adopts a bursting disc type structure.

[0013] Further, the data acquisition system comprises a pressure sensor, a temperature sensor and a flow sensor, all of which adopt an explosion-proof design, and the signal output ends are connected with the intelligent control unit.

[0014] The pressure sensor adopts a diaphragm type pressure transmitter, and the measurement accuracy is not less than 0.2 level; the temperature sensor adopts an armored thermistor, and the temperature measurement range is -40℃ to 200℃; and the flow sensor adopts a vortex flowmeter, and the accuracy level is 0.5 level.

[0015] Further, the predicted pressure of the hydrogen storage cylinder is periodically acquired, specifically: a historical pressure feature set of the hydrogen storage cylinder is acquired, a data prediction model corresponding to the internal pressure is acquired, the historical pressure feature set is taken as input data of the data prediction model, and the predicted pressure of the hydrogen storage cylinder is obtained through output of the data prediction model;

[0016] The historical pressure feature set of the hydrogen storage cylinder is acquired in the following manner: the pressure features of multiple consecutive periods before the current time are acquired, the pressure features of the multiple periods are combined to obtain the historical pressure feature set of the hydrogen storage cylinder.

[0017] The pressure feature of one period is acquired in the following manner: all internal pressures of the hydrogen storage cylinder in one period are acquired, data preprocessing and feature extraction are performed on all the internal pressures to obtain the pressure feature of the period.

[0018] Further, after starting the pressure relief warning, it is determined to start the emergency pressure relief valve, the secondary pressure relief valve or the primary pressure relief valve, specifically: when the pressure relief warning is started, the predicted temperature PTtp and the predicted flow PTin of the hydrogen storage cylinder are acquired, the pressure relief correlation value Bd of the internal temperature and the pressure relief correlation value Es of the medium flow are synchronously acquired, and the formula is used to obtain the explosion-proof pressure relief determination value Sw, the explosion-proof pressure relief determination high value and the explosion-proof pressure relief determination low value are set, when the explosion-proof pressure relief determination value is greater than or equal to the explosion-proof pressure relief determination high value, the emergency pressure relief valve is started, when the explosion-proof pressure relief determination value is between the explosion-proof pressure relief determination high value and the explosion-proof pressure relief determination low value, the secondary pressure relief valve is started, and when the explosion-proof pressure relief determination value is less than or equal to the explosion-proof pressure relief determination low value, the primary pressure relief valve is started.

[0019] Further, the predicted temperature and the predicted flow rate of the hydrogen storage cylinder are obtained, specifically: a historical temperature feature set and a historical flow rate feature set of the hydrogen storage cylinder are obtained, a data prediction model corresponding to the internal temperature and the medium flow rate is obtained, the historical temperature feature set and the historical flow rate feature set are respectively input into the corresponding data prediction model, and the predicted temperature and the predicted flow rate of the hydrogen storage cylinder are output.

[0020] Further, the historical temperature feature set of the hydrogen storage cylinder is obtained in the following manner: temperature features of the hydrogen storage cylinder in a plurality of continuous periods before the current time are obtained, the temperature features of the plurality of periods are combined, and the historical temperature feature set of the hydrogen storage cylinder is obtained.

[0021] The historical flow rate feature set of the hydrogen storage cylinder is obtained in the following manner: flow rate features of the hydrogen storage cylinder in a plurality of continuous periods before the current time are obtained, the flow rate features of the plurality of periods are combined, and the historical flow rate feature set of the hydrogen storage cylinder is obtained.

[0022] Further, the pressure relief correlation value of the internal temperature is obtained in the following manner: an average feature fluctuation value and an average connection feature value of the internal temperature are obtained, and are marked as , the average feature fluctuation value of the internal temperature, the average connection feature value of the internal temperature, an average feature fluctuation value and an average connection feature value of the internal pressure are obtained, and are marked as , the average feature fluctuation value of the internal pressure, the average connection feature value of the internal pressure, and the pressure relief correlation value of the internal temperature is calculated using a cosine similarity algorithm.

[0023] The pressure relief correlation value of the medium flow rate is obtained in the following manner: an average feature fluctuation value and an average connection feature value of the medium flow rate are obtained, and are marked as , the average feature fluctuation value of the medium flow rate, the average connection feature value of the medium flow rate, an average feature fluctuation value and an average connection feature value of the internal pressure are obtained, and are marked as , the average feature fluctuation value of the internal pressure, the average connection feature value of the internal pressure, and the pressure relief correlation value of the medium flow rate is calculated using a cosine similarity algorithm.

[0024] The average feature fluctuation value is obtained in the following manner: feature analysis values of the same parameter in e continuous periods before the current time are obtained, all the feature analysis values are sequentially sorted according to the order of the corresponding periods, the absolute values of the difference values of the adjacent two feature analysis values after sorting are calculated, the average feature fluctuation value is obtained by summing all the feature fluctuation values and taking the average.

[0025] The average connection characteristic value is obtained in the following manner: the characteristic analysis values of the same parameter in the e continuous periods before the current time are obtained, all the characteristic analysis values are sequentially sorted according to the chronological order of the corresponding periods, the adjacent two characteristic analysis values after the sorting are summed to obtain a connection characteristic value, all the connection characteristic values are summed and averaged to obtain the average connection characteristic value.

[0026] Further, a control method of an intelligent explosion-proof pressure relief hydrogen storage cylinder comprises the following steps:

[0027] Step one: periodically obtaining the predicted pressure of the hydrogen storage cylinder;

[0028] Step two: determining whether to start the pressure relief warning based on the comparison result of the predicted pressure and the predicted reference pressure;

[0029] Step three: obtaining the explosion-proof pressure relief determination value after starting the pressure relief warning;

[0030] Step four: starting the emergency pressure relief valve pressure relief when the explosion-proof pressure relief determination value is greater than or equal to the explosion-proof pressure relief determination high value;

[0031] Step five: starting the secondary pressure relief valve pressure relief when the explosion-proof pressure relief determination value is between the explosion-proof pressure relief determination high value and the explosion-proof pressure relief determination low value;

[0032] Step six: starting the primary pressure relief valve pressure relief when the explosion-proof pressure relief determination value is less than or equal to the explosion-proof pressure relief determination low value.

[0033] Compared with the prior art, the present application has the following beneficial effects:

[0034] The control method of the present application can realize accurate regulation of pressure, stable and controllable pressure relief process, and accurate and comprehensive prediction of the subsequent pressure of the hydrogen storage cylinder by combining the LSTM model and the correlation and influence between the internal pressure, internal temperature and medium flow in the hydrogen storage cylinder, and dynamically taking the corresponding pressure relief scheme for pressure relief adjustment, thereby ensuring reasonable and effective pressure relief of the hydrogen storage cylinder. BRIEF DESCRIPTION OF DRAWINGS

[0035] Figure 1 The method flow chart of the control method of the intelligent explosion-proof pressure relief hydrogen storage cylinder;

[0036] Figure 2 The assembly structure diagram of the intelligent explosion-proof pressure relief hydrogen storage cylinder;

[0037] Figure 3 The assembly structure diagram of the multi-stage pressure relief system;

[0038] Figure 4Assemble the structure diagram of the data acquisition system.

[0039] Figure 5 Assemble the structure diagram of the intelligent control system.

[0040] In the figure: 1-hydrogen storage cylinder body, 2-multistage pressure relief system, 21-first stage pressure relief valve, 22-second stage pressure relief valve, 23-emergency pressure relief valve, 3-intelligent control unit, 31-central processing unit, 32-storage module, 33-control execution module, 34-human-computer interaction unit, 4-data acquisition system, 41-pressure sensor, 42-temperature sensor, 43-8 sensor. DETAILED DESCRIPTION

[0041] Example 1: Refer to Figure 1 A control method for an intelligent explosion-proof pressure relief hydrogen storage cylinder, comprising the following steps:

[0042] Step 1: periodically obtain the predicted pressure of the hydrogen storage cylinder;

[0043] Step 2: based on the comparison result of the predicted pressure and the predicted reference pressure, determine whether to start the pressure relief warning;

[0044] Step 3: after starting the pressure relief warning, obtain the explosion-proof pressure relief determination value;

[0045] Step 4: when the explosion-proof pressure relief determination value is greater than or equal to the explosion-proof pressure relief determination high value, start the emergency pressure relief valve pressure relief;

[0046] Step 5: when the explosion-proof pressure relief determination value is between the explosion-proof pressure relief determination high value and the explosion-proof pressure relief determination low value, start the second stage pressure relief valve pressure relief;

[0047] Step 6: when the explosion-proof pressure relief determination value is less than or equal to the explosion-proof pressure relief determination low value, start the first stage pressure relief valve pressure relief.

[0048] Example 2: Refer to Figures 2 to 5 , including hydrogen storage cylinder body 1, multistage pressure relief system 2 fixed on hydrogen storage cylinder body 1, intelligent control unit 3 and data acquisition system 4. Hydrogen storage cylinder body 1 is made of Q345R steel material, the wall thickness is 12mm, and the design pressure is 1.6MPa.

[0049] The multi-stage pressure relief system 2 comprises a first-stage pressure relief valve 21, a second-stage pressure relief valve 22 and an emergency pressure relief valve 23 connected in series. The first-stage pressure relief valve 21 adopts an electrically-controlled regulating valve structure, has a flow capacity of 50 m³ / h at a maximum opening of 100%, can be continuously adjusted within a range of 0-100%, and has a response time of less than 500 ms; the second-stage pressure relief valve 22 adopts a direct-acting electromagnetic valve, is normally closed, has a rated passage diameter of DN50, a rated pressure of PN16, and a response time of less than 100 ms; and the emergency pressure relief valve 23 adopts a bursting disc structure, has a bursting pressure of 1.8 MPa±3%, and a bursting response time of less than 5 ms.

[0050] The data acquisition system 4 is specifically arranged as follows: pressure sensors 41 are installed at the top, middle and bottom of the hydrogen storage cylinder body 1, adopt diaphragm pressure transmitters, have a measurement range of 0-2 MPa, an accuracy level of 0.2, and output a 4-20 mA standard signal; temperature sensors 42 adopt PT100 armored thermistors, are arranged at different heights of the hydrogen storage cylinder body 1, have a temperature measurement range of -40℃ to 200℃, and a response time of less than 10 s; and a flow sensor 43 is installed on the pressure relief pipeline, adopts a DN50 vortex flowmeter, and is used to monitor the medium flow during pressure relief.

[0051] The intelligent control unit 3 adopts an industrial control cabinet structure, and internally installed has a central processing unit 31, a storage module 32, a control execution module 33 and a man-machine interaction unit 34. The central processing unit 31 adopts an industrial-grade ARM processor, has a main frequency of 1.2 GHz, and is equipped with 4 GB of running memory; the storage module 32 adopts a 128 GB industrial-grade solid state disk, and has a power failure protection function; and the man-machine interaction unit 34 adopts a 10-inch capacitive touch screen, has a resolution of 1920×1080, and supports multi-point touch operation.

[0052] The control execution module 33 acquires the internal pressure, internal temperature and medium flow of the hydrogen storage cylinder in real time, periodically acquires the predicted pressure Rk of the hydrogen storage cylinder, sets a predicted reference pressure (the predicted reference pressure is a pre-set pressure value), starts pressure relief warning when the predicted pressure is greater than the predicted reference pressure, and does not make further processing when the predicted pressure is less than or equal to the predicted reference pressure.

[0053] When starting pressure relief warning, the predicted temperature PTtp and the predicted flow PTin of the hydrogen storage cylinder are acquired, the pressure relief correlation value Bd of the internal temperature and the pressure relief correlation value Es of the medium flow are synchronously acquired, and the anti-explosion pressure relief judgment value Sw is obtained by using the formula .

[0054] The pressure relief correlation value of the internal temperature is acquired as follows: the average characteristic fluctuation value and the average connection characteristic value of the internal temperature are acquired, and are marked as , is the average characteristic fluctuation value of the internal temperature, is the average connection characteristic value of the internal temperature, the average characteristic fluctuation value and the average connection characteristic value of the internal pressure are obtained, and are marked as , is the average characteristic fluctuation value of the internal pressure, is the average connection characteristic value of the internal pressure, and the pressure relief correlation value of the internal temperature is calculated using the cosine similarity algorithm.

[0055] The pressure relief correlation value of the medium flow is obtained as follows: the average characteristic fluctuation value and the average connection characteristic value of the medium flow are obtained, and are marked as , is the average characteristic fluctuation value of the medium flow, is the average connection characteristic value of the medium flow, the average characteristic fluctuation value and the average connection characteristic value of the internal pressure are obtained, and are marked as , is the average characteristic fluctuation value of the internal pressure, is the average connection characteristic value of the internal pressure, and the pressure relief correlation value of the medium flow is calculated using the cosine similarity algorithm.

[0056] The pressure relief correlation value of the internal temperature The pressure relief correlation value of the medium flow ;

[0057] The average characteristic fluctuation value is obtained as follows: the characteristic analysis values of the same parameter (the parameters include the internal pressure, the internal temperature, and the medium flow) of the continuous e periods before the current time are obtained, all the characteristic analysis values are sequentially sorted in the order of the corresponding periods, the absolute values of the differences between the adjacent two sorted characteristic analysis values are calculated to obtain the characteristic fluctuation values, all the characteristic fluctuation values are summed and averaged to obtain the average characteristic fluctuation value.

[0058] The average connection characteristic value is obtained as follows: the characteristic analysis values of the same parameter of the continuous e periods before the current time are obtained, all the characteristic analysis values are sequentially sorted in the order of the corresponding periods, the summed values of the adjacent two sorted characteristic analysis values are obtained to obtain the connection characteristic values, all the connection characteristic values are summed and averaged to obtain the average connection characteristic value.

[0059] The explosion-proof pressure relief determination high value and the explosion-proof pressure relief determination low value (the explosion-proof pressure relief determination high value is greater than the explosion-proof pressure relief determination low value, and both the explosion-proof pressure relief determination high value and the explosion-proof pressure relief determination low value are pre-set threshold values) are set, when the explosion-proof pressure relief determination value is greater than or equal to the explosion-proof pressure relief determination high value, the emergency pressure relief valve is started to release pressure, when the explosion-proof pressure relief determination value is between the explosion-proof pressure relief determination high value and the explosion-proof pressure relief determination low value, the secondary pressure relief valve is started to release pressure, and when the explosion-proof pressure relief determination value is less than or equal to the explosion-proof pressure relief determination low value, the primary pressure relief valve is started to release pressure.

[0060] Periodically acquire the predicted pressure of the hydrogen storage cylinder, specifically: acquire a historical pressure feature set of the hydrogen storage cylinder, acquire a data prediction model corresponding to the internal pressure, input the historical pressure feature set into the data prediction model, and output the predicted pressure of the hydrogen storage cylinder from the data prediction model.

[0061] Acquire the predicted temperature and predicted flow of the hydrogen storage cylinder, specifically: acquire a historical temperature feature set and a historical flow feature set of the hydrogen storage cylinder, acquire a data prediction model corresponding to the internal temperature and the medium flow, input the historical temperature feature set and the historical flow feature set into the corresponding data prediction model, and output the predicted temperature and the predicted flow of the hydrogen storage cylinder.

[0062] The historical pressure feature set of the hydrogen storage cylinder is acquired in the following manner: acquire the pressure features of the hydrogen storage cylinder in a plurality of consecutive periods before the current time, combine the pressure features of the plurality of periods, and obtain the historical pressure feature set of the hydrogen storage cylinder.

[0063] The historical temperature feature set of the hydrogen storage cylinder is acquired in the following manner: acquire the temperature features of the hydrogen storage cylinder in a plurality of consecutive periods before the current time, combine the temperature features of the plurality of periods, and obtain the historical temperature feature set of the hydrogen storage cylinder.

[0064] The historical flow feature set of the hydrogen storage cylinder is acquired in the following manner: acquire the flow features of the hydrogen storage cylinder in a plurality of consecutive periods before the current time, combine the flow features of the plurality of periods, and obtain the historical flow feature set of the hydrogen storage cylinder.

[0065] The pressure feature of one period is acquired in the following manner: collect all internal pressures of the hydrogen storage cylinder in one period, perform data preprocessing and feature extraction on all internal pressures (the data preprocessing manner includes data cleaning, and the feature extraction manner includes statistical feature extraction and time series feature extraction), and obtain the pressure feature of the period (the temperature feature and the flow feature of one period are obtained in the same manner, which is not described here).

[0066] Internal pressure, internal temperature, and medium flow rate each correspond to a data prediction model. Each data prediction model is built based on an LSTM model. The construction process of the data prediction model corresponding to internal pressure is as follows: Collect historical pressure feature sets of v hydrogen storage cylinders (if building a data prediction model corresponding to internal temperature, collect historical temperature feature sets of v hydrogen storage cylinders), construct an LSTM model, use the historical pressure feature sets of hydrogen storage cylinders as training data for the LSTM model, assign a predicted pressure to each training data point, and the predicted pressure is the predicted internal pressure of the hydrogen storage cylinder in the next cycle (if building a data prediction model corresponding to internal temperature, assign a predicted temperature to each training data point, and the predicted temperature is the predicted internal temperature of the hydrogen storage cylinder in the next cycle), divide the training data into a training set and a validation set according to a set ratio of 5:1, train the training set and the validation set, and after training, the data prediction model corresponding to internal pressure is constructed.

[0067] Internal pressure, internal temperature, and medium flow rate each correspond to a feature analysis model. Each feature analysis model is built based on a deep learning model. The construction process of the feature analysis model corresponding to internal pressure is as follows: Collect pressure features for L periods (if building a feature analysis model corresponding to internal temperature, collect temperature features for L periods), build a deep learning model, use the historical pressure feature set of the hydrogen storage cylinder as the training data of the deep learning model, assign a feature analysis value to each training data, the value range of the feature analysis value is (3.0~8.0), the larger the feature analysis value, the more abnormal the internal pressure in the period, the smaller the feature analysis value, the more normal the internal pressure in the period (if building a feature analysis model corresponding to internal temperature, the larger the feature analysis value, the more abnormal the internal temperature in the period, the smaller the feature analysis value, the more normal the internal temperature in the period), divide the training data into training set, validation set and test set according to the set ratio of 4:1:1, train the training set, validation set and test set, and complete the training to build the feature analysis model of internal pressure.

[0068] The working process of this invention includes three stages: system initialization, normal operation, and emergency response.

[0069] System initialization phase:

[0070] 1) Power-on self-test: Check whether all sensor signals are normal and whether each actuator is in position;

[0071] 2) Parameter loading: Read control parameters and historical data from storage module 32;

[0072] 3) Communication Confirmation: Establish data communication between modules to ensure normal data transmission;

[0073] 4) Preheat standby: The device enters normal operation state after preheating for 3 minutes.

[0074] Normal operation stage:

[0075] 1) Data acquisition: The system collects pressure, temperature, flow and other parameters at a cycle of 100ms;

[0076] 2) Data processing: The collected data is preprocessed by filtering, calibration and the like;

[0077] 3) Trend prediction: Pressure trend prediction is performed every 1s to predict the pressure change in the next 30s;

[0078] 4) Control decision: The appropriate control strategy is selected according to the prediction result;

[0079] 5) Execution control: The corresponding control action is executed according to the decision result.

[0080] Emergency treatment stage:

[0081] When the following conditions occur, the system enters the emergency treatment stage:

[0082] 1) Rapid pressure rise and exceeding 90% of the set value;

[0083] 2) Main sensor failure;

[0084] 3) Control execution mechanism response anomaly;

[0085] 4) Manual triggering of emergency shutdown.

[0086] After entering the emergency treatment stage, the system will execute the following steps:

[0087] 1) Immediately start the secondary relief valve 22 for rapid pressure relief;

[0088] 2) Sound and light alarm signals are sent to remind the on-site operator;

[0089] 3) The associated feed system is cut off;

[0090] 4) The system state data at the time of failure is recorded;

[0091] 5) If the pressure continues to rise to 1.8MPa, the emergency relief valve 23 will automatically burst.

[0092] Taking an actual application as an example, a typical control process of the present application is illustrated:

[0093] When the system detects that the pressure begins to rise abnormally, the intelligent control unit 3 analyzes the pressure change trend through a deep learning algorithm. If the pressure is predicted to exceed 1.2 MPa in a short period of time, the system first starts the primary pressure relief valve 21 for pre-discharge. The opening degree of the primary pressure relief valve 21 is calculated and adjusted in real time by the control execution module 33, and the initial opening degree is set to 30%, which is then dynamically adjusted according to the pressure change.

[0094] If the primary pressure relief effect is not ideal, and the pressure continues to rise to 1.4 MPa, the system will automatically start the secondary pressure relief valve 22. At this time, the primary pressure relief valve 21 remains fully open, and the secondary pressure relief valve 22 adopts a pulse opening mode, with each opening time being 2s and each closing time being 1s. In this way, the pressure is lowered in steps, avoiding the impact caused by sudden pressure drop.

[0095] When extreme situations occur, such as a serious malfunction of the device causing the pressure to rise sharply, when the pressure reaches 1.8 MPa, the rupture disc of the emergency pressure relief valve 23 will automatically break, completing the pressure relief action within 5ms, ensuring the safety of the device. The system simultaneously records all operating parameters 60s before the failure occurs, providing a basis for subsequent accident analysis.

[0096] The above formulas are all dimensionless numerical calculations, and the preset parameters in the formulas are set by a person skilled in the art according to the actual situation.

[0097] The above embodiments can be realized wholly or partially by software, hardware, firmware or any other combination. When realized by software, the above embodiments can be realized wholly or partially in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are wholly or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another, for example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center through a wired or wireless (such as infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. containing one or more available medium collections. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state disk.

[0098] It should be understood that the magnitude of the sequence number of each process described above does not mean the order of execution, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0099] Those skilled in the art can appreciate that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether the functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. A skilled person can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0100] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

[0101] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0102] If the functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the parts that make contributions to the prior art or parts of the technical solutions can be embodied in the form of software products. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0103] The above merely provides the specific implementation of the present application, but the protection scope of the present application is not limited to this. Any person skilled in the art can easily think of the changes or replacements within the technical range disclosed by the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A hydrogen storage cylinder with intelligent explosion-proof pressure relief, characterized in that, The hydrogen storage cylinder body, the intelligent control unit, the multi-stage pressure relief system and the data acquisition system are included. The intelligent control unit is electrically connected with the hydrogen storage cylinder body. The intelligent control unit periodically acquires the predicted pressure Rk of the hydrogen storage cylinder, determines whether to start the pressure relief warning based on the comparison result of the predicted pressure and the predicted reference pressure, and determines to start the emergency pressure relief valve, the secondary pressure relief valve or the primary pressure relief valve after starting the pressure relief warning. After starting the pressure relief early warning, it is determined to start the emergency pressure relief valve pressure relief, the secondary pressure relief valve pressure relief or the primary pressure relief valve pressure relief, specifically: when starting the pressure relief early warning, the predicted temperature PTtp and the predicted flow PTin of the hydrogen storage cylinder are obtained, the pressure relief correlation value Bd of the internal temperature and the pressure relief correlation value Es of the medium flow are obtained synchronously, and the anti-explosion pressure relief determination value Sw is obtained by using the formula The above formula is a dimensionless value calculation, and the anti-explosion pressure relief determination high value and the anti-explosion pressure relief determination low value are set. When the anti-explosion pressure relief determination value is greater than or equal to the anti-explosion pressure relief determination high value, the emergency pressure relief valve is started to release pressure; when the anti-explosion pressure relief determination value is between the anti-explosion pressure relief determination high value and the anti-explosion pressure relief determination low value, the secondary pressure relief valve is started to release pressure; and when the anti-explosion pressure relief determination value is less than or equal to the anti-explosion pressure relief determination low value, the primary pressure relief valve is started to release pressure. The method for obtaining the relief value and the connection value of the internal pressure is as follows: obtaining the average characteristic fluctuation value and the average connection value of the internal pressure, and marking them as , the average characteristic fluctuation value of the internal pressure, the average connection value of the internal pressure, obtaining the average characteristic fluctuation value and the average connection value of the internal pressure, and marking them as , the average characteristic fluctuation value of the internal pressure, the average connection value of the internal pressure, and calculating the relief correlation value of the internal temperature by using the cosine similarity algorithm. The pressure relief correlation value of the medium flow is obtained as follows: average characteristic fluctuation value and average connection characteristic value of the medium flow are obtained and marked as , is the average characteristic fluctuation value of the medium flow, is the average connection characteristic value of the medium flow, average characteristic fluctuation value and average connection characteristic value of the internal pressure are obtained and marked as , is the average characteristic fluctuation value of the internal pressure, is the average connection characteristic value of the internal pressure, and the pressure relief correlation value of the medium flow is calculated by using a cosine similarity algorithm. The average feature fluctuation value is obtained in the following manner: the feature analysis values of the same parameter in the previous e continuous periods are obtained, all the feature analysis values are sequentially sorted according to the order of the corresponding periods, the absolute values of the difference values of the adjacent two sorted feature analysis values are calculated to obtain the feature fluctuation values, and the average value of the sum of all the feature fluctuation values is obtained to obtain the average feature fluctuation value. The average connection feature value is obtained in the following manner: the feature analysis values of the same parameter in the previous e continuous periods are obtained, all the feature analysis values are sequentially sorted according to the order of the corresponding periods, the sum of the adjacent two sorted feature analysis values is calculated to obtain the connection feature value, and the average value of the sum of all the connection feature values is obtained to obtain the average connection feature value. The multi-stage pressure relief system is fixed on the hydrogen storage cylinder body. The data acquisition system is used to acquire the internal pressure, internal temperature and medium flow of the hydrogen storage cylinder.

2. The intelligent explosion-proof and pressure-relief hydrogen storage cylinder according to claim 1, characterized in that, The multi-stage pressure relief system includes a primary pressure relief valve, a secondary pressure relief valve and an emergency pressure relief valve arranged in series, all of which are electrically connected with the intelligent control unit. 3.The intelligent explosion-proof and pressure-relief hydrogen storage cylinder of claim 2, wherein, The primary pressure relief valve adopts an electrically adjustable valve structure, the secondary pressure relief valve adopts an electromagnetic quick opening and closing valve structure, and the emergency pressure relief valve adopts a bursting disc structure.

4. The intelligent explosion-proof and pressure-relief hydrogen storage cylinder according to claim 1, characterized in that, The data acquisition system includes a pressure sensor, a temperature sensor and a flow sensor, all of which are designed in an explosion-proof manner, and the signal output ends are connected with the intelligent control unit. The pressure sensor adopts a diaphragm type pressure transmitter with a measurement accuracy of not less than 0.2 level, the temperature sensor adopts an armored thermistor with a temperature measurement range of -40℃ to 200℃, and the flow sensor adopts a vortex flowmeter with a precision level of 0.

5.

5. The intelligent explosion-proof and pressure-relief hydrogen storage cylinder according to claim 1, characterized in that, The predicted pressure of the hydrogen storage cylinder is periodically acquired, specifically: a historical pressure feature set of the hydrogen storage cylinder is acquired, a data prediction model corresponding to the internal pressure is acquired, the historical pressure feature set is taken as the input data of the data prediction model, and the predicted pressure of the hydrogen storage cylinder is obtained by the output of the data prediction model; The historical pressure feature set of the hydrogen storage cylinder is obtained in the following manner: the pressure features of the hydrogen storage cylinder in a plurality of continuous periods before the current time are acquired, the pressure features of the plurality of periods are combined to obtain the historical pressure feature set of the hydrogen storage cylinder; The pressure feature of one period is obtained in the following manner: all the internal pressures of the hydrogen storage cylinder in one period are acquired, data preprocessing and feature extraction are performed on all the internal pressures to obtain the pressure feature of the period.

6. The intelligent explosion-proof and pressure-relief hydrogen storage cylinder of claim 1, wherein, The predicted temperature and the predicted flow rate of the hydrogen storage cylinder are obtained, specifically: a historical temperature feature set and a historical flow rate feature set of the hydrogen storage cylinder are obtained, a data prediction model corresponding to the internal temperature and the medium flow rate is obtained, the historical temperature feature set and the historical flow rate feature set are respectively input into the corresponding data prediction model, and the predicted temperature and the predicted flow rate of the hydrogen storage cylinder are obtained by output.

7. The intelligent explosion-proof and pressure-relief hydrogen storage cylinder of claim 6, wherein, The historical temperature feature set of the hydrogen storage cylinder is obtained in the following manner: temperature features of the hydrogen storage cylinder in a plurality of continuous periods before the current time are obtained, the temperature features of the plurality of periods are combined, and the historical temperature feature set of the hydrogen storage cylinder is obtained; The historical flow rate feature set of the hydrogen storage cylinder is obtained in the following manner: flow rate features of the hydrogen storage cylinder in a plurality of continuous periods before the current time are obtained, the flow rate features of the plurality of periods are combined, and the historical flow rate feature set of the hydrogen storage cylinder is obtained. 8.A control method of the intelligent explosion-proof pressure relief hydrogen storage cylinder, applied to the intelligent explosion-proof pressure relief hydrogen storage cylinder of any one of claims 1-7, characterized in that, The method comprises the following steps: Step one: periodically obtaining the predicted pressure of the hydrogen storage cylinder; Step two: determining whether to start the pressure relief warning based on the comparison result of the predicted pressure and the predicted reference pressure; Step three: obtaining the anti-explosion pressure relief determination value after starting the pressure relief warning; Step four: starting the emergency pressure relief valve to release pressure when the anti-explosion pressure relief determination value is greater than or equal to the anti-explosion pressure relief determination high value; Step five: starting the secondary pressure relief valve to release pressure when the anti-explosion pressure relief determination value is between the anti-explosion pressure relief determination high value and the anti-explosion pressure relief determination low value; Step six: starting the primary pressure relief valve to release pressure when the anti-explosion pressure relief determination value is less than or equal to the anti-explosion pressure relief determination low value.

Images