CN112096693B - On-line diagnosis and verification method for underwater production hydraulic control system, storage medium and control terminal - Google Patents
On-line diagnosis and verification method for underwater production hydraulic control system, storage medium and control terminal Download PDFInfo
- Publication number
- CN112096693B CN112096693B CN202010774523.7A CN202010774523A CN112096693B CN 112096693 B CN112096693 B CN 112096693B CN 202010774523 A CN202010774523 A CN 202010774523A CN 112096693 B CN112096693 B CN 112096693B
- Authority
- CN
- China
- Prior art keywords
- control system
- hydraulic control
- valve
- model
- hydraulic
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F15—FLUID-PRESSURE ACTUATORS; HYDRAULICS OR PNEUMATICS IN GENERAL
- F15B—SYSTEMS ACTING BY MEANS OF FLUIDS IN GENERAL; FLUID-PRESSURE ACTUATORS, e.g. SERVOMOTORS; DETAILS OF FLUID-PRESSURE SYSTEMS, NOT OTHERWISE PROVIDED FOR
- F15B19/00—Testing; Calibrating; Fault detection or monitoring; Simulation or modelling of fluid-pressure systems or apparatus not otherwise provided for
- F15B19/005—Fault detection or monitoring
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F15—FLUID-PRESSURE ACTUATORS; HYDRAULICS OR PNEUMATICS IN GENERAL
- F15B—SYSTEMS ACTING BY MEANS OF FLUIDS IN GENERAL; FLUID-PRESSURE ACTUATORS, e.g. SERVOMOTORS; DETAILS OF FLUID-PRESSURE SYSTEMS, NOT OTHERWISE PROVIDED FOR
- F15B19/00—Testing; Calibrating; Fault detection or monitoring; Simulation or modelling of fluid-pressure systems or apparatus not otherwise provided for
- F15B19/007—Simulation or modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Abstract
The invention discloses an online diagnosis and calibration method for an underwater production hydraulic control system, a storage medium and a control terminal, belonging to the technical field of underwater production control and comprising the following steps: acquiring working data of each valve acquired by an underwater production hydraulic control system in real time; importing the working data into a calculation model to draw an actual working curve of each parameter; and comparing the difference between the actual working curve of each parameter in different time periods and the standard curve of the corresponding parameter, judging whether the difference exceeds a preset value, and if so, outputting fault alarm information and a corresponding diagnosis report of the valve performance. The invention ensures that the hydraulic valve fault detection is more accurate and the efficiency is higher.
Description
Technical Field
The invention relates to an online diagnosis and verification method for an underwater production hydraulic control system, a storage medium and a control terminal.
Background
The underwater production hydraulic control system depends on a large number of hydraulic control systems, whether each valve in the hydraulic control system is in a normal working state or not is vital to safety production, and in the prior art, valve sensors or electronic equipment are checked by self and offline simulation data are used as comparison references to judge whether the valves fail or not. However, the off-line simulation data has hysteresis, and the efficiency of judging the working state of the valve is not high.
Disclosure of Invention
In view of this, the technical problem to be solved by the present invention is to provide an online diagnosis and verification method, a storage medium, and a control terminal for an underwater production hydraulic control system, so as to solve the problem in the prior art that the efficiency of determining whether valves and the like in the underwater production hydraulic control system work normally is low.
The present invention has been made to solve the above-mentioned problems,
on one hand, the method for diagnosing and checking the underwater production hydraulic control system on line is applied to a control terminal and comprises the following steps:
acquiring working data of each valve acquired by an underwater production hydraulic control system in real time;
importing the working data into a calculation model to draw an actual working curve of each parameter;
comparing the difference between the actual working curve of each parameter in different time periods and the standard curve of the corresponding parameter,
and judging whether the difference exceeds a preset value, and if so, outputting fault alarm information and a corresponding diagnosis report of the valve performance.
Further, the operation data of each valve includes one or more of a hydraulic supply pressure, an actuator hydraulic pressure, a valve opening time, and an actuator hydraulic pressure, a hydraulic discharge pressure, and a valve closing time during the closing of the valve.
Further, the fault alarm information and the diagnosis report corresponding to the valve performance comprise alarm prompts of whether the hydraulic pressure of the underwater Christmas tree leaks, the leakage amount and the leakage of the hydraulic liquid.
Further, the calculation model is:
firstly, according to an underwater production hydraulic control system model, a simplified flow equation is as follows:
F＝(1-K 0 )*a 1 *(P 1 -P 2 -KZ)+K 0 *F 1p
wherein F is the hydraulic system mass flow rate; k 0 The constant is selectable by a user, and the value range is (0, 1); f 1p F value calculated for the last iteration; p 1 、P 2 Is a position s 1 And position s 2 The pressure of (d);
is a linear coefficient, where p 1 1p 、p 2 1p For the last iteration pressure, KZ ═ ρ g (Z) 1 -Z 2 )，Z 1 、Z 2 Is a position s 1 And s 2 The elevation of the position is shown, rho is the density of the fluid, and g is the acceleration of gravity;
then, constructing a matrix equation set according to the number of the network nodes of the hydraulic system;
iteration is carried out on actual measurement data of the hydraulic control system produced underwater on site, a fuzzy group is set, a fuzzy equation model is established, an extreme learning machine is adopted to calculate and determine a parameter F in the model, and the output of the model is as follows:
F＝Hβ＝∑βg(w·Φ mk (X m ,μ mk )+b)
wherein, F is the output value of the training sample, H is the hidden layer output matrix, beta is the connection weight of the hidden layer and the output layer, g (·) is the activation function of the extreme learning machine, the sigmoid function is selected, w is the connection weight of the input layer and the hidden layer, b is the hidden layer neuron threshold, phi (X, mu) ═ exp (mu) 2 )·X]Representing a new input matrix formed by the input variable X and the membership degree mu of the fuzzy group; the calculation formula of the membership degree is as follows:
represents the m-th training sample X m Membership to fuzzy group k, where c * To blur the number of clusters, v k V and v j Respectively obtaining fuzzy clustering centers by fuzzy clustering;
and finally, removing the suspected failure point according to the model, performing inverse iteration operation by using the rest data, and reversely deducing a theoretical calculation value of the suspected failure point:
wherein, P i 、P j Indicating the pressure measured by the i, j sensors, Z i 、Z j Indicates the elevation at the ith and the j, F ij Representing the mass flow rate between i, j.
Further, the steps are restarted periodically, model parameters are optimized, and the model is automatically learned and maintained.
Further, the step of determining whether the difference exceeds a preset value, and if so, outputting fault alarm information and a corresponding diagnosis report of the valve performance further comprises:
checking the sampled variable parameters one by one, recording the measurement time, comparing the calculated value with the measured value corresponding to the measurement time to obtain the percentage of the difference range, if the percentage of the deviation range exceeds a set threshold, determining that the valve corresponding to the judgment parameter is invalid, and outputting fault alarm information and a diagnosis report of the corresponding valve performance.
Furthermore, abnormal measurement values are eliminated through model calculation, calculation values are obtained, and the calculation values are used for replacing the measurement values so as to eliminate alarm.
And further, inputting the data into a 3D display model, and displaying a failure signal of a corresponding valve in the 3D display model.
Another aspect of the present invention provides a computer readable storage medium storing one or more programs, the one or more programs being executable by one or more processors to perform the steps of any of the above-described methods for online diagnostics and verification of a subsea production hydraulic control system.
Another aspect of the present invention provides a control terminal, including a memory, a processor, and a computer program stored on the memory and executable on the processor; the computer program when executed by the processor implements the steps of any of the above described subsea production hydraulic control system online diagnostic and verification methods.
The online diagnosis and verification method of the underwater production hydraulic control system, the storage medium and the control terminal are realized by establishing a fluid simulation model of the underwater hydraulic control system, substituting parameters such as actual field working conditions (hydraulic system pressure, water depth, environment temperature and the like) into a flow network model in real time for operation and analysis to obtain a logic correct state and parameter values of equipment, and then comparing information such as pressure flow and the like acquired on site with a change curve and a logic correct state value, thereby greatly improving the accuracy of diagnosis. And the flow network model is adopted for judgment, the faults of the related sensors can be effectively identified, and the accuracy and the efficiency of fault judgment can be obviously improved. The system can be applied to monitoring and diagnosis of various underwater hydraulic valves, large-scale engineering equipment and a large number of operating personnel are not required to be moved during operation, and the cost of the personnel and the equipment can be greatly saved.
Drawings
Fig. 1 is a schematic flow chart illustrating an implementation process of an online diagnosis and verification method for a hydraulic control system for underwater production according to a first embodiment of the present invention;
FIG. 2 is a schematic flow chart of an implementation of an online diagnosis and verification method for a hydraulic control system for subsea production according to a second embodiment of the present invention;
fig. 3 is a schematic view of a fluid network according to an embodiment of the present invention.
Detailed Description
In order to make the technical problems, technical solutions and advantageous effects to be solved by the present invention clearer and clearer, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the invention.
Example one
The first embodiment of the invention provides an online diagnosis and verification method for an underwater production hydraulic control system, which comprises the following steps:
s1, acquiring the working data of each valve acquired by the underwater production hydraulic control system in real time;
and the SEM (subsea production control module) reads the pressure, flow signal, Christmas tree pressure, temperature and the like of the hydraulic valve in real time. The hydraulic supply pressure, the actuator hydraulic pressure and the valve opening time of each subsea tree valve in the opening process, and the actuator hydraulic pressure, the hydraulic discharge pressure and the valve closing time of the valve in the closing process are used as working data of each valve.
S2, importing the working data into a calculation model to draw an actual working curve of each parameter;
the calculation model is as follows:
s201, building a flow network model according to the structure of the underwater production hydraulic control system; building a flow network model by using a node method according to a fluid mechanics continuity equation, a momentum equation and an energy equation;
when the number of the flow network nodes is large, the flow network nodes can be simplified into a plurality of small flow networks or systems, so that the modeling process is simplified.
For subsea production hydraulic control systems, the mass flow rate of a node is increased or decreased depending on the actual operating conditions; it is therefore necessary to introduce compressibility and mass imbalance terms into the mathematical equation, which yields:
the mass flow rate of the underwater production hydraulic system is rho vA, rho is the density of fluid in the underwater production hydraulic control system, v is the flow speed, and A is the sectional area of the pipeline; p is the pressure at the node; t is the absolute temperature at the node; α is the compressibility factor.
When the pipe length is L, the conservation of momentum equation can be expressed as:
wherein, P 1 、P 2 Hydraulic control system position s for subsea production 1 Node and location s 2 The pressure at the node; ρ is the fluid density; g is the acceleration of gravity; z 1 、Z 2 Is a position s 1 And s 2 The elevation of the place; h L Head loss; v is the flow rate; in a subsea production hydraulic control system, the head loss term is expressed as: rho gH L ＝F 2 /a 2 Wherein a is calculated from the fluid flow rate, pressure drop and height difference according to the actual flow or design data provided.
Then, equation (2) can be converted to:
using quasi-steady state simplification, the last term can be discarded, further simplifying to:
thus, it is possible to obtain:
F＝a 1 *[P 1 -P 2 -KZ] (5)
wherein, a 1 ＝a/|p 1 1p -p 2 1p -KZ| 1/2 Is a linear coefficient, where p 1 1p 、p 2 1p The last iteration pressure; KZ ═ ρ g (Z) 1 -Z 2 )。
In order to solve the non-convergence iterative process occurring in numerical solution, a relaxation factor K is introduced 0 Then, equation (5) can be transformed into:
F＝a 1 *(P 1 -P 2 -KZ)-K 0 [a 1 *(P 1 -P 2 -KZ)-F 1p ] (6)
equation (6) when arranged results in a simplified flow equation:
F＝(1-K 0 )*a 1 *(P 1 -P 2 -KZ)+K 0 *F 1p (7)
wherein F is the hydraulic system mass flow rate; k 0 The constant is selectable by a user, and the value range is (0, 1); f 1p F value calculated for the last iteration; p 1 、P 2 Is a position s 1 And position s 2 The pressure of (d);
is a linear coefficient, where p 1 1p 、p 2 1p For the last iteration pressure, KZ ═ ρ g (Z) 1 -Z 2 )，Z 1 、Z 2 Is a position s 1 And s 2 The elevation of the position is shown, rho is the density of the fluid, and g is the acceleration of gravity;
in the formula (7), F, P 1 And P 2 As an unknown quantity, KZ is a system constant, F 1p The last iteration value is a known quantity at the time of calculation. The system constant KZ is therefore usually ignored for simplicity of the calculation. Then, as in the flow network in fig. 3, a matrix equation set is constructed according to the network nodes of the hydraulic control system for underwater production as follows:
F 1 ＝(1-K 0 )*a 11 *(P A -P 1 )+K 0 *F 1 1p (8)
F 2 ＝(1-K 0 )*a 12 *(P 2 -P D )+K 0 *F 2 1p (9)
F 3 ＝(1-K 0 )*a 13 *(P 1 -P 3 )+K 0 *F 3 1p (10)
F 4 ＝(1-K 0 )*a 14 *(P 1 -P 4 )+K 0 *F 4 1p (11)
F 5 ＝(1-K 0 )*a 15 *(P 3 -P 2 )+K 0 *F 5 1p (12)
F 6 ＝(1-K 0 )*a 16 *(P 4 -P 2 )+K 0 *F 6 1p (13)
establishing a mass balance equation can obtain:
F 1 -F 3 -F 4 ＝0 (14)
F 5 +F 6 -F 2 ＝0 (15)
in the above formula, the incoming node is denoted by a (+) sign, and the outgoing node is denoted by a (-) sign.
Equations (8) through (15) provide a complete set of eight equations for the eight unknown arguments, i.e., F 1 ，F 2 ，F 3 ，F 4 ，F 5 ，F 6 、P 1 And P 2 . In this problem, a known boundary pressure is given, i.e. the hydraulic supply pressureForce and hydraulic discharge pressure, P 3 And P 4 Is the hydraulic pressure of the actuator 1 and the actuator 2. The system of equations in matrix form is shown below.
S202, iterating actual measurement data of the on-site underwater production hydraulic control system, and calculating and determining a parameter F in the model by using an extreme learning machine so that the model can be used. For the flow network model established in this embodiment, the F value is used as the output, and the other influencing factors (P) 1 、P 2 、P 3 、P 4 、P A 、P D Six modeling variables) as inputs. Setting fuzzy groups and establishing a fuzzy equation, and performing optimization fitting on each fuzzy group by using an extreme learning machine. And the genetic optimization algorithm is adopted to optimize the input weight matrix and the hidden layer bias of the extreme learning machine, so that the problem of unstable model output caused by randomly generating network parameters is solved.
The extreme learning machine combined with the genetic optimization algorithm has global search optimization capability and strong learning capability. Firstly, determining the number of neurons in each layer of the extreme learning machine, setting a maximum evolution algebra M, randomly generating an input weight w and a hidden layer bias b of the extreme learning machine, carrying out binary coding, and initializing a population;
then, aiming at each individual of any generation, calculating an output weight matrix of the extreme learning machine, adopting a root mean square error as an optimization objective function, and calculating individual fitness:
wherein i is the individual sample, N is the total number of samples,
is the predicted output of the sample, F i A target output for the sample; the smaller the value of the objective function, the more accurate the model.
And finally, selecting genetic individuals by roulette according to the fitness of each individual, optimizing through crossing and variation operations to generate a new generation of population, and terminating optimization when the population individuals meet constraint conditions or reach the maximum evolution algebra M to obtain a final population.
And decoding the final population to obtain an input weight w of the extreme learning machine and a hidden layer bias b, and calculating an output layer weight by adopting a least square method. The output model obtained by calculation is as follows:
F＝Hβ＝∑βg(w·Φ mk (X m ,μ mk )+b)
wherein, F is the output value of the training sample, H is the hidden layer output matrix, beta is the connection weight of the hidden layer and the output layer, g (·) is the activation function of the extreme learning machine, the sigmoid function is selected, w is the connection weight of the input layer and the hidden layer, b is the hidden layer neuron threshold, phi (X, mu) ═ exp (mu) 2 )·X]Representing a new input matrix formed by the input variables X and the membership μ of the fuzzy group. The calculation formula of the membership degree is as follows:
represents the m-th training sample X m Membership to fuzzy group k, where c * To blur the number of clusters, v k V and v j The fuzzy clusters are respectively the centers of the fuzzy clusters.
S203, carrying out online diagnosis and verification on the underwater production hydraulic control system, eliminating suspected failure points, carrying out inverse iteration operation by using the rest data, and reversely deducing a theoretical calculation value of the suspected failure points, wherein the calculation formula is as follows:
wherein, P i 、P j Indicating the pressure measured by the i, j sensors, Z i 、Z j Indicates the elevation at the ith and the j, F ij Representing the mass flow rate between i, j.
Under the state of a stable flow field, the data are transmitted to the calculation model for data processing and storage analysis, sampled variables (measuring instrument signals) are checked one by one to form an actuator hydraulic pressure curve, the curve is formed by combining underwater control hydraulic pressure data, and then the curve is compared with two standard hydraulic pressure curves which are stored in a database in advance and used for opening and closing the valve respectively to obtain whether the working state of the valve is normal or not, whether a fault exists or not and what kind of fault exists.
And periodically restarting the steps, and optimizing the model parameters to enable the model to be independently learned and maintained.
S3, comparing the difference between the actual working curve of each parameter and the standard curve of the corresponding parameter in different time periods,
s4, judging whether the difference exceeds a preset value, if so, executing a step S5, otherwise, returning to the step S1;
recording the measuring time, comparing the calculated value with the measured value corresponding to the measuring time to obtain the percentage or variance, mean square error and the like of the difference range, judging whether the difference exceeds a preset value, if so, judging that the hydraulic pressure of the underwater Christmas tree leaks, calculating the leakage amount, displaying the alarm prompt of the hydraulic pressure leakage, and outputting fault alarm information and a grading diagnosis report of the working performance of the valve.
And S5, outputting fault alarm information and a corresponding diagnosis report of the valve performance.
The fault alarm information and the diagnosis report corresponding to the valve performance comprise alarm prompts of whether the hydraulic pressure of the underwater Christmas tree leaks, the leakage amount and the leakage of the hydraulic liquid. In the process of opening each hydraulic valve, the supplied hydraulic pressure and the actuator hydraulic pressure change along with time to form a unique curve, if the actual curve is different from the standard curve when the valve works normally, the valve is indicated to have a fault, and the reason of the problem can be found out by analyzing the difference between the actual curve and the standard curve in different time periods; meanwhile, in the closing process of the hydraulic valve, the discharge hydraulic pressure and the actuator hydraulic pressure of the hydraulic valve also form a special curve different from that in the opening process along with the change of time, and the reason of the valve fault can be found out by analyzing the difference between the actual curve and the standard curve in different time periods; meanwhile, whether the subsea Christmas tree has hydraulic fluid leakage or not can be identified by tracking and analyzing the variation trend of the supply hydraulic pressure, the valve opening and closing times and the hydraulic fluid consumption on the Christmas tree.
Example two
The second embodiment of the invention provides an online diagnosis and verification method for an underwater production hydraulic control system, which comprises the following steps:
s11, acquiring the working data of each valve acquired by the underwater production hydraulic control system in real time;
wherein the operation data of each valve comprises hydraulic supply pressure, actuator hydraulic pressure, valve opening time, and one or more of actuator hydraulic pressure, hydraulic discharge pressure, and valve closing time during the closing of the valve.
S12, importing the working data into a calculation model to draw an actual working curve of each parameter;
s13, comparing the difference between the actual working curve of each parameter and the standard curve of the corresponding parameter in different time periods;
s14, judging whether the difference exceeds a preset value, if so, executing a step S15, otherwise, returning to the step S11;
s15, outputting fault alarm information and a corresponding diagnosis report of valve performance;
and S16, eliminating abnormal measured values through model calculation to obtain calculated values, and replacing the measured values with the calculated values to eliminate alarm.
Theoretical calculation of suspected failure point P i The formula of (1) is:
wherein, P i 、P j Indicating the pressure measured by the i, j sensors, Z i 、Z j Indicates the elevation at the ith and the j, F ij Representing the mass flow rate between i, j. ρ represents a fluid density, g represents a gravitational acceleration, and a is a flow coefficient.
Further, the predefined failure modes include drift, leakage, blockage, failure modes; the flow network knowledge base comprises energy transfer characteristics of flow network nodes and branches; the instrument fault feature library comprises numerical value drift, abnormal change rate, open circuit and short circuit fault features.
And after the suspected failure point is eliminated, performing inverse iteration operation by using the rest data, and reversely deducing a theoretical calculation value of the suspected failure point. And eliminating the change of process conditions, determining the signal health level, and checking the instrument signal and diagnosing the fault by taking the calculated value. And recording the sampling signal and the calculation signal according to the measurement time, and alarming and positioning the fault according to the deterministic fault diagnosis condition. And inputting the data into a 3D display model, and displaying a failure signal of the corresponding valve in the 3D display model.
EXAMPLE III
A third embodiment of the present invention provides a computer-readable storage medium storing one or more programs, the one or more programs being executable by one or more processors to perform the steps shown in embodiment one or embodiment two.
Example four
A fourth embodiment of the present invention provides a control terminal, including a memory, a processor, and a computer program stored on the memory and executable on the processor; the computer program, when executed by the processor, implements the steps shown in either embodiment one or embodiment two.
The preferred embodiments of the present invention have been described above with reference to the accompanying drawings, and the scope of the invention is not limited thereby. Those skilled in the art can implement the invention in various modifications, such as features from one embodiment can be used in another embodiment to yield yet a further embodiment, without departing from the scope and spirit of the invention. Any modification, equivalent replacement and improvement made within the technical idea of using the present invention should be within the scope of the right of the present invention.
Claims (9)
1. An online diagnosis and calibration method for an underwater production hydraulic control system is applied to a control terminal and comprises the following steps:
acquiring working data of each valve acquired by an underwater production hydraulic control system in real time;
importing the working data into a calculation model to draw an actual working curve of each parameter; the calculation model is as follows:
the method comprises the following steps of establishing a flow equation of an underwater production hydraulic control system model:
F＝(1-K 0 )*a 1 *(P 1 -P 2 -KZ)+K 0 *F 1p
wherein F is the hydraulic system mass flow rate; k 0 The constant is selectable by a user, and the value range is (0, 1); f 1p F value calculated for the last iteration; p 1 、P 2 Is a position s 1 And position s 2 The pressure of (d);
is a linear coefficient, where p 1 1p 、p 2 1p For the last iteration pressure, KZ ═ ρ g (Z) 1 -Z 2 )，Z 1 、Z 2 Is a position s 1 And s 2 The elevation of the position is shown, rho is the density of the fluid, and g is the acceleration of gravity;
constructing a matrix equation set according to the number of the network nodes of the hydraulic system;
iteration is carried out on actual measurement data of the hydraulic control system produced underwater on site, a fuzzy group is set, a fuzzy equation model is established, an extreme learning machine is adopted to calculate and determine a parameter F in the model, and the output of the model is as follows:
F＝Hβ＝Σβg(w·Φ mk (X m ,μ mk )+b)
wherein F is the output value of the training sample, H is the hidden layer output matrix, beta is the connection weight of the hidden layer and the output layer, g (-) is the activation function of the extreme learning machine, the sigmoid function is selected, w is the connection weight of the input layer and the hidden layer, b is the hidden layerNeuron threshold, Φ (X, μ) ═ exp (μ) 2 )·X]Representing a new input matrix formed by the input variable X and the membership degree mu of the fuzzy group; the calculation formula of the membership degree is as follows:
represents the m-th training sample X m Membership degree of fuzzy group k, wherein c is fuzzy group number, v k V and v j Respectively as fuzzy cluster centers, and solving by fuzzy clustering;
and (3) eliminating the suspected failure point according to the model, performing inverse iteration operation by using the rest data, and reversely deducing a theoretical calculation value of the suspected failure point:
wherein, P i 、P j Indicating the pressure measured by the i, j sensors, Z i 、Z j Indicates the elevation at the ith and the j, F ij Representing the mass flow rate between i and j, a being the flow coefficient calculated from the fluid flow rate, pressure drop and height difference;
comparing the difference between the actual working curve of each parameter in different time periods and the standard curve of the corresponding parameter,
and judging whether the difference exceeds a preset value, and if so, outputting fault alarm information and a corresponding diagnosis report of the valve performance.
2. The subsea production hydraulic control system on-line diagnostic and verification method according to claim 1, characterized in that:
the operating data for each valve includes hydraulic supply pressure, actuator hydraulic pressure, valve open time, and one or more of actuator hydraulic pressure, hydraulic drain pressure, valve close time during valve closing.
3. The subsea production hydraulic control system on-line diagnostic and verification method according to claim 1, characterized in that: the fault alarm information and the diagnosis report corresponding to the valve performance comprise alarm prompts of whether the hydraulic pressure of the underwater Christmas tree leaks, the leakage amount and the leakage of the hydraulic liquid.
4. The subsea production hydraulic control system on-line diagnostic and verification method according to claim 1, characterized in that:
and periodically restarting the steps, and optimizing the model parameters to enable the model to be independently learned and maintained.
5. The on-line diagnosis and verification method for the underwater hydraulic control system according to claim 1, wherein the step of determining whether the difference exceeds a preset value, and if so, outputting fault alarm information and a corresponding diagnosis report of valve performance further comprises:
checking the sampled variable parameters one by one, recording the measurement time, comparing the calculated value with the measured value corresponding to the measurement time to obtain the percentage of the difference range, if the percentage of the difference range exceeds a set threshold, determining that the valve corresponding to the judgment parameter is invalid, and outputting fault alarm information and a diagnosis report of the corresponding valve performance.
6. The subsea production hydraulic control system on-line diagnostic and verification method according to claim 5, characterized by: and eliminating abnormal measured values through model calculation to obtain calculated values, and replacing the measured values with the calculated values to eliminate alarm.
7. The subsea production hydraulic control system on-line diagnostic and verification method according to claim 5, characterized by: and inputting the working data into a 3D display model, and displaying a failure signal of the corresponding valve in the 3D display model.
8. A computer readable storage medium, wherein the computer readable storage medium stores one or more programs which are executable by one or more processors to perform the steps of the method for online diagnostics and verification of a subsea production hydraulic control system of any of claims 1-7.
9. A control terminal comprising a memory, a processor and a computer program stored on the memory and executable on the processor; the computer program when executed by the processor performs the steps of the method for on-line diagnostics and verification of a subsea production hydraulic control system according to any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010774523.7A CN112096693B (en) | 2020-08-04 | 2020-08-04 | On-line diagnosis and verification method for underwater production hydraulic control system, storage medium and control terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010774523.7A CN112096693B (en) | 2020-08-04 | 2020-08-04 | On-line diagnosis and verification method for underwater production hydraulic control system, storage medium and control terminal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112096693A CN112096693A (en) | 2020-12-18 |
| CN112096693B true CN112096693B (en) | 2022-09-20 |
Family
ID=73749942
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010774523.7A Active CN112096693B (en) | 2020-08-04 | 2020-08-04 | On-line diagnosis and verification method for underwater production hydraulic control system, storage medium and control terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112096693B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112963406B (en) * | 2021-03-31 | 2023-06-02 | 上海电气集团股份有限公司 | Monitoring method, device and system of hydraulic system and storage medium |
| CN113205248B (en) * | 2021-04-27 | 2023-03-24 | 西安热工研究院有限公司 | Regulating valve fault early warning system and method based on big data medium parameter diagnosis |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2275946A1 (en) * | 2005-03-04 | 2011-01-19 | STMicroelectronics S.r.l. | Probabilistic neural network and relative training method |
| GB0517349D0 (en) * | 2005-08-24 | 2005-10-05 | Isis Innovation | Biomolecular structure determination |
| CN101944141A (en) * | 2010-08-18 | 2011-01-12 | 北京理工大学 | High-efficiency global optimization method using adaptive radial basis function based on fuzzy clustering |
| CN105021382B (en) * | 2014-06-06 | 2017-11-21 | 中国海洋石油总公司 | Subsea production tree hydraulic valve performance on-line monitoring and diagnostic system and method |
| CN104462850A (en) * | 2014-12-25 | 2015-03-25 | 江南大学 | Multi-stage batch process soft measurement method based on fuzzy gauss hybrid model |
| CN107422299A (en) * | 2017-05-03 | 2017-12-01 | 惠州学院 | A kind of mixed source localization method and mixed source alignment system |
-
2020
- 2020-08-04 CN CN202010774523.7A patent/CN112096693B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN112096693A (en) | 2020-12-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7069269B2 (en) | Semi-supervised methods and systems for deep anomaly detection for large industrial surveillance systems based on time series data using digital twin simulation data | |
| CN110441065B (en) | Gas turbine on-line detection method and device based on LSTM | |
| CN111258297B (en) | Equipment health index construction and service life prediction method based on data fusion network | |
| CN112096693B (en) | On-line diagnosis and verification method for underwater production hydraulic control system, storage medium and control terminal | |
| GB2362481A (en) | Evolution of performance model | |
| JP2021121888A (en) | Learning device, learning method, learning program, determination device, determination method, and determination program | |
| CN116448419A (en) | Zero sample bearing fault diagnosis method based on depth model high-dimensional parameter multi-target efficient optimization | |
| CN107491840B (en) | Flow wear characteristic prediction and service life evaluation method based on ELM neural network model | |
| EP3904987B1 (en) | Control support apparatus, control support method, control support program, computer readable medium with control support program recorded thereon and control system | |
| Qin et al. | Remaining useful life prediction for rotating machinery based on optimal degradation indicator | |
| CN115438726A (en) | Device life and fault type prediction method and system based on digital twin technology | |
| CN116861694A (en) | Cable temperature prediction method based on artificial intelligence | |
| CN115114822A (en) | Method and system for estimating residual service life of underwater throttle valve based on digital twinning | |
| CN112229624A (en) | Pneumatic regulating valve fault diagnosis method based on low-deviation random configuration network | |
| CN115081484A (en) | Aircraft engine sensor fault diagnosis method based on CRJ-OSELM algorithm | |
| Kumar | Remaining useful life prediction of aircraft engines using hybrid model based on artificial intelligence techniques | |
| Zhang | Optimum sensor localization/selection in a diagnostic/prognostic architecture | |
| CN111443602B (en) | Hidden Markov-based valve health degree estimation and life prediction method | |
| CN117090831A (en) | Hydraulic system fault diagnosis framework with twinning application layer | |
| CN115618735A (en) | Facility structure health monitoring method based on digital twins and related device | |
| CN110705186B (en) | Real-time online instrument checksum diagnosis method through RBF particle swarm optimization algorithm | |
| CN114936520A (en) | Steam turbine fault early warning analysis method based on improved MSET | |
| CN110705187B (en) | Instant on-line instrument checksum diagnosis method through least square algorithm | |
| CN110705152B (en) | Acceleration sensor arrangement method for monitoring earthquake resistance of building electromechanical pipeline | |
| Tang et al. | Fault detection and diagnosis of pneumatic control valve based on fuzzy method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |