CN110700810A - Drilling platform safety system for testing and monitoring method thereof - Google Patents
Drilling platform safety system for testing and monitoring method thereof Download PDFInfo
- Publication number
- CN110700810A CN110700810A CN201910869418.9A CN201910869418A CN110700810A CN 110700810 A CN110700810 A CN 110700810A CN 201910869418 A CN201910869418 A CN 201910869418A CN 110700810 A CN110700810 A CN 110700810A
- Authority
- CN
- China
- Prior art keywords
- pressure
- pipeline
- temperature
- pressure relief
- upstream
- 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.)
- Granted
Links
- 238000012360 testing method Methods 0.000 title claims abstract description 82
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000012544 monitoring process Methods 0.000 title claims abstract description 30
- 238000005553 drilling Methods 0.000 title claims abstract description 21
- 238000001514 detection method Methods 0.000 claims abstract description 29
- 239000004576 sand Substances 0.000 claims abstract description 28
- RWSOTUBLDIXVET-UHFFFAOYSA-N Dihydrogen sulfide Chemical compound S RWSOTUBLDIXVET-UHFFFAOYSA-N 0.000 claims abstract description 27
- 229910000037 hydrogen sulfide Inorganic materials 0.000 claims abstract description 27
- 230000008569 process Effects 0.000 claims abstract description 27
- 238000013528 artificial neural network Methods 0.000 claims abstract description 12
- 238000011144 upstream manufacturing Methods 0.000 claims description 48
- 239000007789 gas Substances 0.000 claims description 30
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 claims description 28
- 210000002569 neuron Anatomy 0.000 claims description 23
- 239000003345 natural gas Substances 0.000 claims description 14
- 238000005070 sampling Methods 0.000 claims description 11
- 230000006870 function Effects 0.000 claims description 10
- 238000000926 separation method Methods 0.000 claims description 9
- 230000005284 excitation Effects 0.000 claims description 3
- 229910052739 hydrogen Inorganic materials 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 2
- 239000000523 sample Substances 0.000 description 17
- 238000012545 processing Methods 0.000 description 14
- 238000012549 training Methods 0.000 description 13
- 238000013461 design Methods 0.000 description 8
- 230000005540 biological transmission Effects 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 5
- 230000007246 mechanism Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 210000004027 cell Anatomy 0.000 description 3
- 238000002474 experimental method Methods 0.000 description 3
- 239000007787 solid Substances 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 239000012530 fluid Substances 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 239000003921 oil Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 231100000572 poisoning Toxicity 0.000 description 1
- 230000000607 poisoning effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000013024 troubleshooting Methods 0.000 description 1
Images
Classifications
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21B—EARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- E21B44/00—Automatic control systems specially adapted for drilling operations, i.e. self-operating systems which function to carry out or modify a drilling operation without intervention of a human operator, e.g. computer-controlled drilling systems; Systems specially adapted for monitoring a plurality of drilling variables or conditions
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21B—EARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- E21B47/00—Survey of boreholes or wells
-
- 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
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B19/00—Alarms responsive to two or more different undesired or abnormal conditions, e.g. burglary and fire, abnormal temperature and abnormal rate of flow
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mining & Mineral Resources (AREA)
- Geology (AREA)
- Geochemistry & Mineralogy (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Fluid Mechanics (AREA)
- Environmental & Geological Engineering (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Geophysics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Pipeline Systems (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention discloses a drilling platform safety system for testing, which comprises: the detection module is used for detecting the temperature, pressure, sand content, vibration state, pipe wall thickness and hydrogen sulfide content in the pipeline in the test operation process; the pressure relief devices are respectively arranged in a driller room on the drill floor, a choke manifold, a separator of the test area, a data acquisition room of the test area and a position of a living area close to the test area, and are used for relieving pressure to complete the cut-off of the flow in the pipe; and the controller is connected with the detection module and the pressure relief device and used for receiving the detection data of the detection module and controlling the pressure relief device to work. The invention also provides a monitoring method of the safety system of the drilling platform for testing, which is used for acquiring the temperature, the pressure, the sand content, the vibration state, the pipe wall thickness and the hydrogen sulfide content in the pipeline in the testing operation process, determining the working state of the pressure relief device based on the BP neural network and ensuring the field operation safety under the condition of high-temperature and high-pressure wells with large yield.
Description
Technical Field
The invention relates to the field of oil and natural gas exploration and test, in particular to a drilling platform safety system for testing and a monitoring method thereof.
Background
At present, with the continuous development of offshore oil and gas resource exploitation, the testing type is continuously advanced towards a high-temperature high-pressure high-yield well, a testing area is gradually expanded towards a deep water area, for the testing operation of the ultrahigh-temperature high-pressure well, the requirement on operation equipment is stricter, the pressure grade of ground high-pressure equipment reaches 15000Psi, the effective control of high-yield natural gas in the testing process is realized, and the safe operation is the key point in the testing process. Therefore, it is necessary to develop a safety system and a monitoring method for a drilling platform for testing, so as to substantially ensure the smooth implementation of the testing operation and the safe production of the testing platform.
Disclosure of Invention
The invention aims to design and develop a drilling platform safety system for testing, which is provided with pressure relief devices at different positions, and ensures the operation safety of the drilling platform by determining the working states of the pressure relief devices through a detection module.
The invention also aims to design and develop a monitoring method of the safety system of the drilling platform for testing, which collects the temperature, the pressure, the sand content, the vibration state, the pipe wall thickness and the hydrogen sulfide content in the pipeline in the testing operation process, and determines the alarm state and the working state of the pressure relief device based on the BP neural network.
The invention can also accurately control the pressure released by the pressure relief device when the pressure relief device works, finishes the cut-off of the flow in the pipe and ensures the safety of field operation under the condition of high-temperature and high-pressure well large yield.
The technical scheme provided by the invention is as follows:
a test rig safety system, comprising:
the detection module is used for detecting the temperature, pressure, sand content, vibration state, pipe wall thickness and hydrogen sulfide content in the pipeline in the test operation process;
the pressure relief devices are respectively arranged in a driller room of the drill floor, a manifold of a choke in a test area, a separator in the test area, a data acquisition room in the test area and a position of a living area close to the test area, and are used for relieving pressure and finishing the cut-off of the flow in the pipe;
and the controller is connected with the detection module and the pressure relief device and used for receiving the detection data of the detection module and controlling the pressure relief device to work.
Preferably, the detection module includes:
the sand content sensor is arranged in front of the oil nozzle manifold and used for detecting the sand content in the gas in the pipeline;
a vibration sensor disposed on the pipeline in the upstream high-pressure region for detecting a vibration amplitude of the pipeline;
a wall thickness sensor provided at a turning position of the upstream pipeline, for detecting a wall thickness of the pipeline;
a gas sensor, which is arranged on a natural gas pipeline of the separator and is used for detecting the content of the hydrogen sulfide;
a plurality of temperature and pressure sensors disposed respectively upstream of the choke manifold, downstream of the choke manifold and on the separator for detecting pressure and temperature upstream of the choke manifold, temperature and pressure downstream of the choke manifold, pressure at the separation location, temperature of the oil and gas lines.
Preferably, the system also comprises an alarm system which is connected with the detection module and is used for receiving the detection data of the detection module and giving an alarm.
A monitoring method for a safety system of a drilling platform for testing collects the temperature, pressure, sand content, vibration state, pipe wall thickness and hydrogen sulfide content in a pipeline in the testing operation process, and determines the alarm state and the working state of a pressure relief device based on a BP neural network, and specifically comprises the following steps:
measuring the temperature, pressure, sand content, vibration state, pipe wall thickness and hydrogen sulfide content in a pipeline through a sensor according to a sampling period;
step two, determining an input layer neuron vector x ═ x of the three-layer BP neural network1,x2,x3,x4,x5,x6,x7,x8,x9,x10,x11}; wherein x is1Is the sand content, x, in the gas in front of the nozzle manifold2Is the vibration intensity, x, of the upstream high pressure zone line3Is the wall thickness at the turn of the upstream pipeline, x4Is the content of hydrogen sulfide, x, in the natural gas pipeline5Pressure upstream of the nozzle manifold, x6Is the temperature, x, upstream of the nozzle manifold7Pressure downstream of the nozzle manifold, x8Is the temperature, x, downstream of the nozzle manifold9Pressure at separate locations, x10To separate the temperature, x, of the oil line at the location11Is the temperature of the gas line at the separation location;
mapping the input layer vector to a hidden layer, wherein the number of neurons of the hidden layer is m;
step four, obtaining an output layer neuron vector o ═ o1,o2,o3,o4,o5,o6}; wherein o is1Is the working state of the pressure relief device of the driller's room at the drill floor, o2Is the working state of the pressure relief device at the nozzle manifold, o3Operating state of pressure relief means in the separator position, o4Is the working state of a pressure relief device in a data acquisition room, o5Is the working state of the pressure relief device in the living area o6For the working state of the alarm system, the neuron value of the output layer is
k is the output layer neuron sequence number, k is {1,2,3,4,5,6}, and when okIs at 1, is in working state, when okAt 0, is atA non-operating state.
Preferably, when the pressure relief device works, the pressure released by the pressure relief device is controlled to meet the following requirements:
wherein P is the pressure released by the pressure relief device, omega is the sand content in the gas in front of the oil nozzle manifold,
is the content of hydrogen sulfide in the natural gas pipeline,
is the safe content of hydrogen sulfide, H, in the natural gas pipelineAIs the vibration intensity of the upstream high-pressure zone pipeline, HA0Is the standard vibration intensity, T, of the pipeline in the upstream high-pressure regionuTemperature upstream of the nozzle manifold, TdTemperature downstream of the nozzle manifold, TgTo separate the temperature of the gas line at the location, TlFor separating the temperature of the oil line at the location, PuPressure upstream of the nozzle manifold, PdPressure downstream of the choke manifold, PfPressure at the separation position, PAIs unit pressure, d0Is the initial wall thickness at the upstream pipeline bend, d is the real-time wall thickness at the upstream pipeline bend, P0To set the pressure.
Preferably, the vibration severity of the upstream high pressure zone line is:
in the formula, HAIs the vibration intensity of the pipeline in the upstream high-voltage area, N is the sampling frequency in a sampling period, H is the vibration frequency of the pipeline in a sampling period, AjIs the amplitude of the pipeline at the jth sample in a sample period.
Preferably, the number of neurons in the hidden layer is 12.
Preference is given toThe excitation functions of the hidden layer and the output layer adopt S-shaped functions fj(x)＝1/(1+e-x)。
The invention has the following beneficial effects:
(1) the safety system for the drilling platform for the test is designed and developed, the pressure relief devices are arranged at different positions, and the working states of the pressure relief devices are determined through the detection module, so that the safety of the operation of the drilling platform is ensured.
(2) The monitoring method for the safety system of the drilling platform for testing, which is designed and developed by the invention, is used for collecting the temperature, the pressure, the sand content, the vibration state, the pipe wall thickness and the hydrogen sulfide content in a pipeline in the testing operation process, and determining the alarm state and the working state of a pressure relief device based on a BP neural network. And the pressure released by the pressure relief device can be accurately controlled when the pressure relief device works, the flow in the pipe is cut off, and the field operation safety under the condition of high-temperature high-pressure well large yield is ensured.
Drawings
FIG. 1 is a schematic view of a rig safety system for testing according to the present invention.
Detailed Description
The present invention is further described in detail below with reference to the attached drawings so that those skilled in the art can implement the invention by referring to the description text.
As shown in fig. 1, the present invention provides a rig safety system for testing, comprising: the detection module is used for detecting the temperature, pressure, sand content, vibration state, pipe wall thickness and hydrogen sulfide content in the pipeline in the test operation process; the pressure relief devices (the pressure relief device 1, the pressure relief device 2, the pressure relief device 3, the pressure relief device 4 and the pressure relief device 5) are respectively arranged at a driller room of the drill floor, a manifold of a choke in a test area, a separator in the test area, a data acquisition room in the test area and a position of a living area close to the test area and are used for relieving pressure and finishing the cut-off of an in-pipe process; and the controller (an actuating mechanism of the electro-hydraulic quick turn-off system) is connected with the detection module and the pressure relief device and is used for receiving the detection data of the detection module and controlling the pressure relief device to work.
In the embodiment, when equipment connection and installation are carried out in the early stage of test operation, an actuating mechanism of an electro-hydraulic rapid shutoff system (controller) is installed in a wellhead high-pressure area, and trigger mechanisms (pressure relief devices) are respectively arranged at five different places of a test area and are respectively positioned at a driller room of a drill floor, a choke manifold of the test area, a separator of the test area, a data acquisition room of the test area and a living area close to the test area so as to ensure that the flow shutoff is carried out on the position close to the wellhead in the first time under emergency, shutoff signals are transmitted by electric signals, once problems are found, the signals are transmitted to a signal processing box of the rapid shutoff system within 3 seconds through a flow network arranged in advance, an electro-hydraulic conversion valve in the signal processing box starts to work, a hydraulic pressure relief device is triggered to prompt the flow of the actuating mechanism to be shut off, and downstream, avoiding greater safety accidents.
And in the working process of the system, the acousto-optic alarm facility is triggered to remind an operator that the electro-hydraulic emergency shutdown system works. The signal of the electro-hydraulic system can be simultaneously inserted into the data processing system, so that the on-line monitoring, emergency troubleshooting, confirmation and resetting of the trigger signal and the like of the turn-off signal and the turn-off system are realized, and the electro-hydraulic emergency turn-off system is the first important means for ensuring the safety of the test process. The system comprises a signal control logic design system, a multipoint electro-hydraulic control starting design, an explosion-proof design, a safety logic design, a display and data interaction design and a signal data processing design, and forms a set of complete safety control turn-off flow. In addition, different operating pressures are set through the high-low pressure alarm, the high-low pressure alarm is installed according to the pressure range of the test process, relevant signals are transmitted to the signal processing box, the shutoff system can timely cut off process fluid under the condition of overpressure or low pressure, and the safety of field operation equipment is guaranteed.
Contain sand on-line monitoring system and install on the data head in nozzle manifold the place ahead of test flow, there is intervention formula sensor probe (sand content sensor), when having gas in the flow through, if mix in the gas sand body or the solid of small particle size, can be at the response curve of the in-process change sensor through the probe, through data transmission line data transmission to the data acquisition processing system who monitors, the change of curve and number value can appear in monitoring system, and then confirm sand content, make operating personnel can know to have sand body or solid particle in the flow, take measures, avoid downstream equipment to appear damaging, guarantee the safety of equipment, thereby guarantee the safety of whole test system, guarantee operation safety.
The vibration monitoring is also installed at the key position of the testing process, most probes are arranged on the pipeline of a high-pressure area at the upstream of the testing process, 3-4 monitoring points are set, a non-intrusive type is adopted, a detector (a vibration sensor) is connected to a data acquisition and processing system through a sensing line, and the vibration curve of the process pipeline is observed on a monitoring interface of the system. If the flow suddenly has abnormal conditions, the flow pipeline shakes or vibrates, data can be transmitted to the data acquisition and processing system through the vibration monitoring system, and the situation shows that solid gravel or hydrate is possibly generated in the flow to cause blockage, or the connected test flow pipeline is loosened due to long-time abnormal shaking, so that the connection pipeline of the flow is tripped, and gas leakage or flow damage is caused.
The online wall thickness monitoring system consists of a data probe (a wall thickness sensor), a data excitation device, a data receiving and processing device and a data sending device. The system is arranged at the turning position of an upstream pipeline of a testing process, and is excited by a timing signal, a data probe measures the thickness of the outer wall of the pipeline at the mounting position, the measured data is received and processed by a receiving device and converted into an electric signal which is sent to a data acquisition and processing system by a data sending device to generate real-time data, if the process is carried out, fluid in the testing process continuously erodes the pipeline of the process, so that the wall thickness thinning degree of the pipeline exceeds the allowable use range of the pipeline, the system can give an alarm, prompt field operation personnel, and avoid the pipeline from leaking and injuring people.
The on-line hydrogen sulfide monitoring system comprises a gas probe (a gas sensor), a transmission pipeline, a data processing terminal and a signal output device. The gas content detection device is arranged on a natural gas pipeline of a separator, can realize online real-time gas contact and gas transfer, can detect the gas content regularly, can timely transmit data to a data acquisition and processing system through a data transmission line if the occurrence and the content of hydrogen sulfide are monitored to exceed a safe allowable range, plays a role in reminding field operation personnel, avoids hydrogen sulfide poisoning of operating personnel, and ensures the safety of field operation.
The on-line pressure and temperature recording and monitoring system is characterized in that a sensor (a temperature and pressure sensor) is arranged on a specific position and specific equipment, including an upstream oil nozzle manifold, a downstream oil nozzle manifold and a separator, and is used for respectively monitoring the pressure and the temperature of the upstream oil nozzle manifold, the temperature and the pressure of the downstream oil nozzle manifold, the pressure of a separation position, the temperature of an oil pipeline and a gas pipeline and simultaneously recording the flow of oil, gas and water of the separator. The data remote transmission, recording and processing of the test system are realized mainly by using the data sensor, the data transmission line, the signal collector, the signal receiver and the signal processing terminal, complete data information is provided for test operation, and the smooth implementation of the test operation is ensured.
The safety system for the drilling platform for the test is designed and developed, the pressure relief devices are arranged at different positions, and the working states of the pressure relief devices are determined through the detection module, so that the safety of the operation of the drilling platform is ensured.
The invention also provides a monitoring method of the drilling platform safety system for testing, which is used for acquiring the temperature, the pressure, the sand content, the vibration state, the pipe wall thickness and the hydrogen sulfide content in the pipeline in the testing operation process, and determining the alarm state and the working state of the pressure relief device based on the BP neural network, and specifically comprises the following steps:
step one, establishing a BP neural network model.
Fully interconnected connections are formed among neurons of each layer on the BP model, the neurons in each layer are not connected, and the output and the input of neurons in an input layer are the same, namely oi＝xi. The operating characteristics of the neurons of the intermediate hidden and output layers are
opj＝fj(netpj)
Where p represents the current input sample, ωjiIs the connection weight from neuron i to neuron j, opiIs the current input of neuron j, opjIs the output thereof; f. ofjIs a non-linear, slightly non-decreasing function, generally taken as a sigmoid function, i.e. fj(x)＝1/(1+e-x)。
The BP network system structure adopted by the invention consists of three layers, wherein the first layer is an input layer, n nodes are provided in total, n detection signals representing the working state of the equipment system are correspondingly provided, and the signal parameters are given by a data preprocessing module; the second layer is a hidden layer, and has m nodes which are determined by the training process of the network in a self-adaptive mode; the third layer is an output layer, p nodes are provided in total, and the output is determined by the response actually needed by the system.
The mathematical model of the network is:
inputting a vector: x ═ x1,x2,...,xn)T
Intermediate layer vector: y ═ y1,y2,...,ym)T
Outputting a vector: o ═ o (o)1,o2,...,op)T
In the invention, the number of nodes of an input layer is n equals to 11, the number of nodes of an output layer is p equals to 6, and the number of nodes of a hidden layer is m equals to 12.
The 11 parameters of the input layer are respectively expressed as: x is the number of1Is the sand content, x, in the gas in front of the nozzle manifold2Is the vibration intensity, x, of the upstream high pressure zone line3Is the wall thickness at the turn of the upstream pipeline, x4Is the content of hydrogen sulfide, x, in the natural gas pipeline5Pressure upstream of the nozzle manifold, x6Is the temperature, x, upstream of the nozzle manifold7Pressure downstream of the nozzle manifold, x8Is the temperature, x, downstream of the nozzle manifold9Pressure at separate locations, x10To separate the temperature, x, of the oil line at the location11Is the temperature of the gas line at the separation location;
the output layer 6 parameters are respectively expressed as: o1Is the working state of the pressure relief device of the driller's room at the drill floor, o2Is the working state of the pressure relief device at the nozzle manifold, o3Operating state of pressure relief means in the separator position, o4Is the working state of a pressure relief device in a data acquisition room, o5Is the working state of the pressure relief device in the living area o6For the working state of the alarm system, the neuron value of the output layer isk is the output layer neuron sequence number, k is {1,2,3,4,5,6}, and when okIs at 1, is in working state, when okWhen 0, it is in the non-operating state.
And step two, training the BP neural network.
After the BP neural network node model is established, the training of the BP neural network can be carried out. And obtaining a training sample according to historical experience data of the product, and giving a connection weight between the input node i and the hidden layer node j and a connection weight between the hidden layer node j and the output layer node k.
(1) Training method
Each subnet adopts a separate training method; when training, firstly providing a group of training samples, wherein each sample consists of an input sample and an ideal output pair, and when all actual outputs of the network are consistent with the ideal outputs of the network, the training is finished; otherwise, the ideal output of the network is consistent with the actual output by correcting the weight; the output samples for each subnet training are shown in table 1.
TABLE 1 output samples for network training
(2) Training algorithm
The BP network is trained by using a back Propagation (Backward Propagation) algorithm, and the steps can be summarized as follows:
the first step is as follows: and selecting a network with a reasonable structure, and setting initial values of all node thresholds and connection weights.
The second step is that: for each input sample, the following calculations are made:
(a) forward calculation: for j unit of l layer
In the formula (I), the compound is shown in the specification,for the weighted sum of the j unit information of the l layer at the nth calculation,
is the connection weight between the j cell of the l layer and the cell i of the previous layer (i.e. the l-1 layer),
is the previous layer (i.e. l-1 layer, node number n)l-1) The operating signal sent by the unit i; when i is 0, order
Is the threshold of the j cell of the l layer.
If the activation function of the unit j is a sigmoid function, then
And is
If neuron j belongs to the first hidden layer (l ═ 1), then there are
If neuron j belongs to the output layer (L ═ L), then there are
(b) And (3) calculating the error reversely:
for output unit
Pair hidden unit
(c) Correcting the weight value:
The third step: inputting a new sample or a new period sample until the network converges, and randomly re-ordering the input sequence of the samples in each period during training.
The BP algorithm adopts a gradient descent method to solve the extreme value of a nonlinear function, and has the problems of local minimum, low convergence speed and the like. A more effective algorithm is a Levenberg-Marquardt optimization algorithm, which enables the network learning time to be shorter and can effectively inhibit the network from being locally minimum. The weight adjustment rate is selected as
Δω＝(JTJ+μI)-1JTe
Wherein J is a Jacobian (Jacobian) matrix of error to weight differentiation, I is an input vector, e is an error vector, and the variable mu is a scalar quantity which is self-adaptive and adjusted and is used for determining whether the learning is finished according to a Newton method or a gradient method.
When the system is designed, the system model is a network which is only initialized, the weight needs to be learned and adjusted according to data samples obtained in the using process, and therefore the self-learning function of the system is designed. Under the condition of appointing learning samples and quantity, the system can carry out self-learning so as to continuously improve the network performance.
When pressure relief device during operation, the pressure that control pressure relief device leaked satisfies:
wherein P is the pressure released by the pressure relief device, omega is the sand content in the gas in front of the oil nozzle manifold,
is the content of hydrogen sulfide in the natural gas pipeline,is the safe content of hydrogen sulfide, H, in the natural gas pipelineAIs the vibration intensity of the upstream high-pressure zone pipeline, HA0Is the standard vibration intensity, T, of the pipeline in the upstream high-pressure regionuTemperature upstream of the nozzle manifold, TdTemperature downstream of the nozzle manifold, TgTo separate the temperature of the gas line at the location, TlFor separating the temperature of the oil line at the location, PuPressure upstream of the nozzle manifold, PdPressure downstream of the choke manifold, PfPressure at the separation position, PAIs unit pressure, d0Is the initial wall thickness at the upstream pipeline bend, d is the real-time wall thickness at the upstream pipeline bend, P0To set the pressure.
The vibration intensity of the pipeline in the upstream high-pressure area is as follows:
in the formula, HAIs the vibration intensity of the pipeline in the upstream high-voltage area, N is the sampling frequency in a sampling period, H is the vibration frequency of the pipeline in a sampling period, AjIs the amplitude of the pipeline at the jth sample in a sample period.
The method for monitoring the safety system of the test rig provided by the invention is further described below with reference to specific embodiments. The environment within 10 different sets of test lines was simulated as shown in table 2.
TABLE 2 simulation data
The monitoring method of the safety system of the drilling platform for testing provided by the invention is adopted to determine the working states of the pressure relief device and the alarm system, and observe the corresponding blank experiment (namely, the safety system of the drilling platform for testing provided by the invention is not adopted), and the specific results are shown in table 3.
TABLE 3 results of the experiment
| Serial number | Working point of pressure relief device | Alarm system | Safety feature | Safety of blank experiment |
| 1 | Pressure relief device 1 | Work by | Security | Is not safe |
| 2 | Pressure relief device 3 | Work by | Security | Is not safe |
| 3 | Pressure relief device 5 | Work by | Security | Is not safe |
| 4 | Pressure relief device 1 | Work by | Security | Is not safe |
| 5 | All are not working | Not working | Security | Security |
| 6 | Pressure relief device 2 | Work by | Security | Is not safe |
| 7 | Pressure relief device 4 | Work by | Security | Is not safe |
| 8 | Pressure relief device 3 | Work by | Security | Is not safe |
| 9 | Pressure relief device 2 | Work by | Security | Is not safe |
| 10 | Pressure relief device 5 | Work by | Security | Is not safe |
As can be seen from Table 3, the monitoring method of the test drilling platform safety system provided by the invention ensures the safety of field operation under the condition of high-temperature and high-pressure wells and large yield.
The monitoring method for the safety system of the drilling platform for testing, which is designed and developed by the invention, is used for collecting the temperature, the pressure, the sand content, the vibration state, the pipe wall thickness and the hydrogen sulfide content in a pipeline in the testing operation process, and determining the alarm state and the working state of a pressure relief device based on a BP neural network. And the pressure released by the pressure relief device can be accurately controlled when the pressure relief device works, the flow in the pipe is cut off, and the field operation safety under the condition of high-temperature high-pressure well large yield is ensured.
While embodiments of the invention have been described above, it is not limited to the applications set forth in the description and the embodiments, which are fully applicable in various fields of endeavor to which the invention pertains, and further modifications may readily be made by those skilled in the art, it being understood that the invention is not limited to the details shown and described herein without departing from the general concept defined by the appended claims and their equivalents.
Claims (8)
1. A test rig safety system, comprising:
the detection module is used for detecting the temperature, pressure, sand content, vibration state, pipe wall thickness and hydrogen sulfide content in the pipeline in the test operation process;
the pressure relief devices are respectively arranged in a driller room of the drill floor, a manifold of a choke in a test area, a separator in the test area, a data acquisition room in the test area and a position of a living area close to the test area, and are used for relieving pressure and finishing the cut-off of the flow in the pipe;
and the controller is connected with the detection module and the pressure relief device and used for receiving the detection data of the detection module and controlling the pressure relief device to work.
2. The test rig safety system of claim 1, wherein the detection module comprises:
the sand content sensor is arranged in front of the oil nozzle manifold and used for detecting the sand content in the gas in the pipeline;
a vibration sensor disposed on the pipeline in the upstream high-pressure region for detecting a vibration amplitude of the pipeline;
a wall thickness sensor provided at a turning position of the upstream pipeline, for detecting a wall thickness of the pipeline;
a gas sensor, which is arranged on a natural gas pipeline of the separator and is used for detecting the content of the hydrogen sulfide;
a plurality of temperature and pressure sensors disposed respectively upstream of the choke manifold, downstream of the choke manifold and on the separator for detecting pressure and temperature upstream of the choke manifold, temperature and pressure downstream of the choke manifold, pressure at the separation location, temperature of the oil and gas lines.
3. The method of monitoring a test rig safety system as recited in claim 1 or 2 further comprising an alarm system coupled to the detection module for receiving detection data from the detection module and for providing an alarm.
4. The monitoring method for the safety system of the drilling platform for the test is characterized by acquiring the temperature, the pressure, the sand content, the vibration state, the pipe wall thickness and the hydrogen sulfide content in a pipeline in the test operation process, and determining the alarm state and the working state of a pressure relief device based on a BP neural network, and specifically comprises the following steps:
measuring the temperature, pressure, sand content, vibration state, pipe wall thickness and hydrogen sulfide content in a pipeline through a sensor according to a sampling period;
step two, determining an input layer neuron vector x ═ x of the three-layer BP neural network1,x2,x3,x4,x5,x6,x7,x8,x9,x10,x11}; wherein x is1Is the sand content, x, in the gas in front of the nozzle manifold2Is the vibration intensity, x, of the upstream high pressure zone line3Is the wall thickness at the turn of the upstream pipeline, x4Is the content of hydrogen sulfide, x, in the natural gas pipeline5Pressure upstream of the nozzle manifold, x6Is the temperature, x, upstream of the nozzle manifold7Pressure downstream of the nozzle manifold, x8Is the temperature, x, downstream of the nozzle manifold9Pressure at separate locations, x10To separate the temperature, x, of the oil line at the location11Is the temperature of the gas line at the separation location;
mapping the input layer vector to a hidden layer, wherein the number of neurons of the hidden layer is m;
step four, obtaining an output layer neuron vector o ═ o1,o2,o3,o4,o5,o6}; wherein o is1Is the working state of the pressure relief device of the driller's room at the drill floor, o2Is the working state of the pressure relief device at the nozzle manifold, o3Operating state of pressure relief means in the separator position, o4For data acquisition in housesWorking state of the pressure relief device o5Is the working state of the pressure relief device in the living area o6For the working state of the alarm system, the neuron value of the output layer is
k is the output layer neuron sequence number, k is {1,2,3,4,5,6}, and when okIs at 1, is in working state, when okWhen 0, it is in the non-operating state.
5. The method of monitoring a test rig safety system of claim 4, wherein the pressure relief device is controlled to relieve when the pressure relief device is activated to a pressure level that satisfies:
wherein P is the pressure released by the pressure relief device, omega is the sand content in the gas in front of the oil nozzle manifold,
is the content of hydrogen sulfide in the natural gas pipeline,is the safe content of hydrogen sulfide, H, in the natural gas pipelineAIs the vibration intensity of the upstream high-pressure zone pipeline, HA0Is the standard vibration intensity, T, of the pipeline in the upstream high-pressure regionuTemperature upstream of the nozzle manifold, TdTemperature downstream of the nozzle manifold, TgTo separate the temperature of the gas line at the location, TlFor separating the temperature of the oil line at the location, PuPressure upstream of the nozzle manifold, PdPressure downstream of the choke manifold, PfPressure at the separation position, PAIs unit pressure, d0Is the initial wall thickness at the upstream pipeline bend, d is the real-time wall thickness at the upstream pipeline bend, P0To set the pressure.
6. The method of monitoring a test rig safety system of claim 5, wherein the vibration severity of the upstream high pressure zone line is:
in the formula, HAIs the vibration intensity of the pipeline in the upstream high-voltage area, N is the sampling frequency in a sampling period, H is the vibration frequency of the pipeline in a sampling period, AjIs the amplitude of the pipeline at the jth sample in a sample period.
7. The method of monitoring a test rig safety system of claim 4,5, or 6, wherein the hidden layer has 12 neurons.
8. The method of monitoring a test rig safety system of claim 7, wherein the hidden layer and the output layer have excitation functions that are sigmoid functions fj(x)＝1/(1+e-x)。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910869418.9A CN110700810B (en) | 2019-09-16 | 2019-09-16 | Drilling platform safety system for testing and monitoring method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910869418.9A CN110700810B (en) | 2019-09-16 | 2019-09-16 | Drilling platform safety system for testing and monitoring method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110700810A true CN110700810A (en) | 2020-01-17 |
| CN110700810B CN110700810B (en) | 2022-03-11 |
Family
ID=69195387
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910869418.9A Active CN110700810B (en) | 2019-09-16 | 2019-09-16 | Drilling platform safety system for testing and monitoring method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110700810B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113341066A (en) * | 2021-05-24 | 2021-09-03 | 西南石油大学 | Multi-sensor fusion technology-based on-line detection method and system for tetrahydrothiophene concentration |
| CN113931625A (en) * | 2020-06-29 | 2022-01-14 | 中国石油天然气股份有限公司 | Oil well ground oil testing system |
| WO2023115281A1 (en) * | 2021-12-20 | 2023-06-29 | 烟台杰瑞石油服务集团股份有限公司 | Method and apparatus for determining fault occurring in high-pressure manifold, and high-pressure manifold system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201593387U (en) * | 2010-02-03 | 2010-09-29 | 中国石油天然气集团公司 | Drilling annulus pressure precise control system |
| CN101852076A (en) * | 2010-03-31 | 2010-10-06 | 中国石油天然气集团公司 | Underground working condition simulation method for controlled pressure drilling experiment and test |
| CN201705322U (en) * | 2010-03-31 | 2011-01-12 | 中国石油天然气集团公司 | Downhole working condition simulating device for pressure control drilling experiments and tests |
| CN102359353A (en) * | 2011-09-22 | 2012-02-22 | 中国石油集团川庆钻探工程有限公司 | Closed-loop pressure control drilling system |
| CN102418509A (en) * | 2010-09-28 | 2012-04-18 | 中国石油化工集团公司 | Indoor test system and method for managed pressure drilling technology |
| CN203847100U (en) * | 2014-06-03 | 2014-09-24 | 中国石油化工股份有限公司 | Remote pressure display system for cable blowout preventing device |
| CN108825146A (en) * | 2018-07-04 | 2018-11-16 | 中海艾普油气测试（天津）有限公司 | A kind of erection joint and installation method for deepwater semisubmersible platform exploration test jobs well head testing tree |
| CN109899011A (en) * | 2019-04-10 | 2019-06-18 | 四川恒铭泽石油天然气工程有限公司 | A kind of oil/gas well full-automatic electric throttling control pressure system |
-
2019
- 2019-09-16 CN CN201910869418.9A patent/CN110700810B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201593387U (en) * | 2010-02-03 | 2010-09-29 | 中国石油天然气集团公司 | Drilling annulus pressure precise control system |
| CN101852076A (en) * | 2010-03-31 | 2010-10-06 | 中国石油天然气集团公司 | Underground working condition simulation method for controlled pressure drilling experiment and test |
| CN201705322U (en) * | 2010-03-31 | 2011-01-12 | 中国石油天然气集团公司 | Downhole working condition simulating device for pressure control drilling experiments and tests |
| CN102418509A (en) * | 2010-09-28 | 2012-04-18 | 中国石油化工集团公司 | Indoor test system and method for managed pressure drilling technology |
| CN102359353A (en) * | 2011-09-22 | 2012-02-22 | 中国石油集团川庆钻探工程有限公司 | Closed-loop pressure control drilling system |
| CN203847100U (en) * | 2014-06-03 | 2014-09-24 | 中国石油化工股份有限公司 | Remote pressure display system for cable blowout preventing device |
| CN108825146A (en) * | 2018-07-04 | 2018-11-16 | 中海艾普油气测试（天津）有限公司 | A kind of erection joint and installation method for deepwater semisubmersible platform exploration test jobs well head testing tree |
| CN109899011A (en) * | 2019-04-10 | 2019-06-18 | 四川恒铭泽石油天然气工程有限公司 | A kind of oil/gas well full-automatic electric throttling control pressure system |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113931625A (en) * | 2020-06-29 | 2022-01-14 | 中国石油天然气股份有限公司 | Oil well ground oil testing system |
| CN113341066A (en) * | 2021-05-24 | 2021-09-03 | 西南石油大学 | Multi-sensor fusion technology-based on-line detection method and system for tetrahydrothiophene concentration |
| CN113341066B (en) * | 2021-05-24 | 2022-04-08 | 西南石油大学 | Multi-sensor fusion technology-based on-line detection method and system for tetrahydrothiophene concentration |
| WO2023115281A1 (en) * | 2021-12-20 | 2023-06-29 | 烟台杰瑞石油服务集团股份有限公司 | Method and apparatus for determining fault occurring in high-pressure manifold, and high-pressure manifold system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110700810B (en) | 2022-03-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110700810B (en) | Drilling platform safety system for testing and monitoring method thereof | |
| US11346200B2 (en) | Method and system for guaranteeing safety of offshore oil well control equipment | |
| CN101012913A (en) | Chaos analysis and micro-processor based conduit pipe micro-leakage diagnosing method and device | |
| CN101592288B (en) | Method for identifying pipeline leakage | |
| CN103530818B (en) | A kind of water supply network modeling method based on BRB system | |
| CN201898519U (en) | Equipment maintenance early-warning device with risk control | |
| CN109838696A (en) | Pipeline fault diagnostic method based on convolutional neural networks | |
| EP3884253B1 (en) | Method and system to analyse pipeline condition | |
| CN103032064A (en) | Method and device for detecting gas cut position in drilling process | |
| CN111695465B (en) | Pipe network fault diagnosis and positioning method and system based on pressure wave mode identification | |
| US20230013006A1 (en) | A system for monitoring and controlling a dynamic network | |
| CN106594526B (en) | A kind of water supply network state monitoring method and device based on hydraulic pressure sampled data | |
| WO2021022315A1 (en) | Method and system to monitor pipeline condition | |
| WO2020040800A1 (en) | Method and system for non-intrusively determining cross-sectional variation for a fluidic channel | |
| CN114819677A (en) | Multi-factor fusion well control risk dynamic quantitative evaluation method and system | |
| AU2019394685B2 (en) | Detecting and quantifying liquid pools in hydrocarbon fluid pipelines | |
| CN112016766A (en) | Oil and gas well drilling overflow and leakage early warning method based on long-term and short-term memory network | |
| CN109902265B (en) | Underground early warning method based on hidden Markov model | |
| CN117345660A (en) | Method, device, equipment and storage medium for monitoring cavitation state of centrifugal pump | |
| CN108952637B (en) | Underwater tree safety system and method for hydrate inhibition in deepwater operation | |
| Wu et al. | A detection and diagnosis method for tubing leakage below liquid level in gas wellbore | |
| CN111598366A (en) | Real-time drilling auxiliary decision-making method and system | |
| CN108825146B (en) | Mounting joint and mounting method for wellhead test tree of deepwater semi-submersible platform exploration test operation | |
| CN103337000A (en) | Safety monitoring and prewarning method for oil-gas gathering and transferring system | |
| Wassar et al. | Model-Based Health Monitoring of Annular Blowout Preventers |
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 |