CN108952637B

CN108952637B - Underwater tree safety system and method for hydrate inhibition in deepwater operation

Info

Publication number: CN108952637B
Application number: CN201810722730.0A
Authority: CN
Inventors: 孙维洲; 关利军; 田向东; 杨昆; 魏安超; 茅春; 蒋政达
Original assignee: Cosl Expro Testing Services Tianjin Co ltd
Current assignee: Cosl Expro Testing Services Tianjin Co ltd
Priority date: 2018-07-04
Filing date: 2018-07-04
Publication date: 2020-08-14
Anticipated expiration: 2038-07-04
Also published as: CN108952637A

Abstract

The invention discloses an underwater tree safety system for hydrate inhibition in deepwater operation, which comprises: inhibitor injection points which are arranged between the underwater trees at equal intervals along the axial direction of the underwater trees; a first injection valve provided at the inhibitor injection point for injecting a thermodynamic inhibitor; a second injection valve provided at the inhibitor injection point for injecting a kinetic inhibitor; a winch connected to the subsea tree for controlling the subsea tree to move axially along the downhole string such that the inhibitor injection point covers the entire downhole string. The underwater pipe column can be monitored at multiple points, and efficient hydrate inhibition is achieved. The invention also discloses an underwater tree safety inhibition method for hydrate inhibition in deepwater operation, which is characterized in that the opening of the first injection valve and the second injection valve and the addition depth of the inhibitor are determined based on the BP neural network, the addition amount of the thermodynamic inhibitor and the kinetic inhibitor can be controlled, and the formation of the hydrate is effectively inhibited.

Description

Underwater tree safety system and method for hydrate inhibition in deepwater operation

Technical Field

The invention relates to the technical field of offshore deepwater oil and gas exploration, in particular to an underwater tree safety system and an underwater tree safety method for hydrate inhibition in deepwater operation.

Background

At present, the current technical situation is that petroleum and natural gas in the stratum are led to the ground for data recording during operation. However, in the process of leading the petroleum and the natural gas to the ground, due to the changes of pressure and temperature, particularly the temperature of seawater close to zero degree near the seabed, hydrates are easily formed in the pipe column, and once the hydrates are formed, the damage or the blockage of the oil pipe can be caused quickly, so that the safety of the whole operation platform is threatened, and the huge exploration investment is abandoned.

The existing tubular column process cannot monitor the temperature change of petroleum and natural gas, cannot inject hydrate inhibitor, and can only close the safety valve in emergency. However, once the pipe column is punctured below the safety valve, the safety valve cannot guarantee safety, so that the whole operation is exposed to danger.

According to research, the hydrate is changed from obvious temperature and pressure when being formed in an oil pipe, and the hydrate is an optimal inhibition point at the initial formation stage, but the existing technology cannot monitor the data change and misses the optimal inhibition period, so that huge hidden troubles are left for the safety of deepwater test operation.

Disclosure of Invention

The invention aims to design and develop an underwater tree safety system for hydrate inhibition in deepwater operation, which can carry out multi-point monitoring on an underwater pipe column and achieve efficient hydrate inhibition.

Another object of the present invention is to design and develop a safety inhibition method for underwater trees for hydrate inhibition in deep water operation, which determines the opening of the first injection valve and the second injection valve and the adding depth of the inhibitor based on the BP neural network, and effectively inhibits the formation of hydrate.

The invention can also control the adding amount of the thermodynamic inhibitor and the kinetic inhibitor according to the opening state of the first injection valve and the second injection valve, thereby effectively inhibiting the formation of hydrate.

The technical scheme provided by the invention is as follows:

an underwater tree safety system for hydrate inhibition in deepwater operations, comprising:

inhibitor injection points which are arranged between the underwater trees at equal intervals along the axial direction of the underwater trees;

a first injection valve provided at the inhibitor injection point for injecting a thermodynamic inhibitor;

a second injection valve provided at the inhibitor injection point for injecting a kinetic inhibitor;

a winch connected to the subsea tree for controlling the subsea tree to move axially along the downhole string such that the inhibitor injection point covers the entire downhole string.

Preferably, the method further comprises the following steps:

the temperature sensors are arranged on the inner wall surface, the outer wall surface and the seabed mud surface of the underground pipe column at equal intervals and are used for detecting the temperature;

pressure sensors respectively provided at the temperature sensors for detecting pressure;

depth sensors provided at the temperature sensors, respectively, for detecting a depth;

and the controller is connected with the temperature sensor, the pressure sensor, the first injection valve, the second injection valve and the winch and is used for receiving detection data of the temperature sensor and the pressure sensor and controlling the first injection valve, the second injection valve and the winch to work.

Correspondingly, the invention also provides a method for safely inhibiting the underwater tree for hydrate inhibition in deepwater operation, which is used for determining the adding depth of the inhibitor and the states of the first injection valve and the second injection valve based on the BP neural network when the underground operation is carried out, and comprises the following steps:

step 1: measuring the internal temperature and pressure, the external temperature and pressure of the underground pipe column and the temperature and pressure of the seabed mud surface through sensors according to a sampling period;

step 2: determining input layer neuron vector x ═ { x) of three-layer BP neural network₁,x₂,x₃,x₄,x₅,x₆}; wherein x is₁Is the internal temperature, x, of the downhole string₂Is the internal pressure of the tubular string, x₃Is the external temperature, x, of the downhole string₄Is a wellOutside temperature of lower tubular column, x₅Is the temperature at the mud surface of the sea bed, x₆The pressure at the mud surface of the seabed is obtained;

and step 3: the input layer vector is mapped to a middle layer, and the number of neurons in the middle layer is m;

step 4: obtaining output layer neuron vector o ═ o₁,o₂,o₃}; wherein o is₁State of the first filling valve, o₂State of the second filling valve, o₃For the depth of addition of inhibitor, the output layer neuron value is

k is output layer neuron sequence number, k is {1,2}, when o_k At 1, the injection valve is in the open state, when o_k At 0, the fill valve is in a closed state.

Preferably, the number m of the intermediate layer nodes satisfies:

wherein n is the number of nodes of the input layer, and p is the number of nodes of the output layer.

Preferably, the excitation functions of the intermediate layer and the output layer both adopt S-shaped functions f_j(x)＝1/(1+e^-x)。

Preferably, when o₁＝1,o₂When the content is 0, the amount of the thermodynamic inhibitor is controlled as follows:

wherein m is_t0The amount of the thermodynamic inhibitor when the inhibitor is only the thermodynamic inhibitor, rho is the density of water, Delta T is the temperature drop for forming hydrate, α is the ratio of the concentration of the thermodynamic inhibitor in the substance to be collected to the concentration of the thermodynamic inhibitor in the aqueous solution, M is the molecular weight of the thermodynamic inhibitor, K is a constant, Q is the flow rate of the substance to be collected in the column, C is the molar concentration of the thermodynamic inhibitor, pi is the circumferential ratio, r is the inner diameter of the column, and l is the influence of the thermodynamic inhibitor added into the columnThe zone height.

Preferably, when o₁＝0,o₂When 1, the amount of the kinetic inhibitor is controlled to be:

wherein m is_d0The amount of kinetic inhibitor when the inhibitor is only kinetic inhibitor, ρ is the density of water, π is the circumference ratio, r is the internal diameter of the column and l is the height of the zone of the column affected by the addition of the kinetic inhibitor.

Preferably, when o₁＝1,o₂When the ratio is 1, the amount of the thermodynamic inhibitor and the kinetic inhibitor is controlled to be respectively as follows:

wherein m is_t1The amount of thermodynamic inhibitor in the inhibitor, m_d1The amount of the kinetic inhibitor in the inhibitor, rho is the density of water, Delta T is the temperature drop for forming hydrate, α is the ratio of the concentration of the thermodynamic inhibitor in the substance to be collected to the concentration of the thermodynamic inhibitor in the aqueous solution, M is the molecular weight of the thermodynamic inhibitor, K is a constant, Q is the flow rate of the substance to be collected in the column, C is the molar concentration of the thermodynamic inhibitor, pi is the circumferential ratio, r is the inner diameter of the column, and l is the height of the region in the column affected by the addition of the inhibitor.

The invention has the following beneficial effects:

(1) the underwater tree safety system for hydrate inhibition in deepwater operation can monitor underwater pipe columns at multiple points, and achieves efficient hydrate inhibition.

(2) The underwater tree safety inhibition method for hydrate inhibition in deepwater operation disclosed by the invention determines the opening of the first injection valve and the second injection valve and the addition depth of the inhibitor based on the BP neural network, so that the hydrate formation is efficiently inhibited. And the addition amount of a thermodynamic inhibitor and a kinetic inhibitor can be controlled according to the opening state of the first injection valve and the second injection valve, so that the formation of hydrate is effectively inhibited.

Drawings

Fig. 1 is a schematic diagram of an underwater tree safety system for hydrate inhibition in deep water operation according to the invention.

FIG. 2 is a temperature pressure phase curve for simulation check of hydrate formation 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 an underwater tree safety system for hydrate inhibition in deepwater operations, comprising: inhibitor injection points which are arranged between the underwater trees at equal intervals along the axial direction of the underwater trees; a first injection valve provided at the inhibitor injection point for injecting a thermodynamic inhibitor; a second injection valve provided at the inhibitor injection point for injecting a kinetic inhibitor; a winch connected to the subsea tree for controlling the subsea tree to move axially along the downhole string such that the inhibitor injection point covers the entire downhole string. Further comprising: the temperature sensors are arranged on the inner wall surface, the outer wall surface and the seabed mud surface of the underground pipe column at equal intervals and are used for detecting the temperature; pressure sensors respectively provided at the temperature sensors for detecting pressure; depth sensors provided at the temperature sensors, respectively, for detecting a depth; and the controller (a bottom electric control panel) is connected with the temperature sensor, the pressure sensor, the first injection valve, the second injection valve and the winch and is used for receiving the detection data of the temperature sensor and the pressure sensor and controlling the first injection valve, the second injection valve and the winch to work.

The kinetic inhibitors are water soluble or water dispersible polymers that inhibit hydrate formation only in the aqueous phase, and are added at very low concentrations (typically less than 1% in the aqueous phase) without affecting the thermodynamic conditions of hydrate formation. In the initial stage of hydrate crystal nucleation and growth, they are adsorbed on the surface of hydrate particles, and the cyclic structure of the inhibitor is combined with the crystals of the hydrate through hydrogen bonds to delay the hydrate crystal nucleation time or prevent further growth of the crystals so that the fluid in the column flows at a temperature lower than the hydrate formation temperature (i.e., at a certain supercooling degree) without hydrate blockage, and PVP (polyvinylpyrrolidone), ethyl methacrylate, N-acylpolyolefin imine, N-vinyl caprolactam, N-alkylacrylamide, polyisopropylmethacrylamide, 2-propyl-2-imidazoline, and the like are generally used.

The thermodynamic inhibitor reduces the activity coefficient of water by changing the thermodynamic generation conditions of three-phase equilibrium of the substance to be exploited, water and hydrate, so that higher pressure or lower temperature is required for generating the hydrate, and the hydrate is not easily formed under the temperature and pressure conditions of a common oil and gas pipeline. Thermodynamic inhibitors are mainly alcohols (methanol, ethylene glycol, diethylene glycol) and sodium chloride solution.

The underwater tree safety system for hydrate inhibition in deepwater operation can monitor underwater pipe columns at multiple points, and achieves efficient hydrate inhibition.

The invention also provides an underwater tree safety inhibition method for hydrate inhibition in deepwater operation, which is used for determining the adding depth of the inhibitor and the states of the first injection valve and the second injection valve based on the BP neural network when the underground operation is carried out, and 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 o_i＝x_i. The operating characteristics of the neurons of the intermediate hidden and output layers are:

o_pj＝f_j(net_pj)

where p represents the current input sample, ω_jiIs the connection weight from neuron i to neuron j, o_piIs the current input of neuron j, o_pjIs the output thereof; f. of_jIs a non-linear, slightly non-decreasing function, generally taken as a sigmoid function, i.e. f_j(x)＝1/(1+e^-x)。

The BP network system structure adopted by the invention comprises three layers, wherein the first layer is an input layer, n nodes are provided in total, n detection signals representing underground pipe columns are correspondingly provided, and the signal parameters are given by a data preprocessing module; the second layer is an intermediate layer (hidden layer) which has m nodes and is 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,...,x_n)^T

Intermediate layer vector: y ═ y₁,y₂,...,y_m)^T

Outputting a vector: o ═ o (o)₁,o₂,...,o_p)^T

In the invention, the number of nodes of the input layer is n equals to 6, the number of nodes of the output layer is p equals to 3, and the number of nodes of the hidden layer is determined according to

And determining that m is 5.

The input layer 6 parameters are respectively expressed as: x is the number of₁Is the internal temperature, x, of the downhole string₂Is the internal pressure of the tubular string, x₃Is the external temperature, x, of the downhole string₄Is the external temperature, x, of the downhole string₅Is the temperature at the mud surface of the sea bed, x₆The pressure at the mud surface of the seabed is obtained;

the output layer has 3 parameters expressed as: o₁State of the first filling valve, o₂State of the second filling valve, o₃For the depth of addition of inhibitor, the output layer neuron value is

k is output layer neuron sequence number, k is {1,2}, when o_kAt 1, the injection valve is in the open state, when o_kAt 0, the fill valve is in a closed 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.

The historical empirical data is obtained according to the hydrate formation simulation check, the depth of the position is determined according to the temperature and the pressure of the formed hydrate, and the formation of the hydrate can be effectively prevented by adding an inhibitor at the position. The temperature and pressure at which hydrates are formed are shown in table 1, and the temperature pressure phase diagram is shown in fig. 2.

TABLE 1 temperature and pressure for hydrate formation

(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 2.

TABLE 2 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

And e_j(n)＝x_j(n)-o_j(n)；

(b) And (3) calculating the error reversely:

for output unit

Pair hidden unit

(c) Correcting the weight value:

η is the learning rate.

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＝(J^TJ+μI)^-1J^Te

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 determining the depth of addition of inhibitor and the state of the first and second injection valves:

(1) when o is₁＝1,o₂When the content is 0, the amount of the thermodynamic inhibitor is controlled as follows:

wherein m is_t0The amount (kg) of the thermodynamic inhibitor when the inhibitor is only the thermodynamic inhibitor, and ρ is the density of water (kg/m)³) Where Δ T is the temperature drop (. degree. C.) for forming a hydrate, α is the ratio of the concentration of the thermodynamic inhibitor in the substance to be collected to the concentration of the thermodynamic inhibitor in the aqueous solution, M is the molecular weight (kg/mol) of the thermodynamic inhibitor, K is a constant, and Q is the flow rate (M) of the substance to be collected in the column (M)³) C is the molar concentration (mol/m) of the thermodynamic inhibitor³) And pi is the circumferential ratio, r is the inner diameter (m) of the column, and l is the height (m) of the region affected by the thermodynamic inhibitor added into the column.

(2) When o is₁＝0,o₂When 1, the amount of the kinetic inhibitor is controlled to be:

wherein m is_d0The amount (kg) of kinetic inhibitor when the inhibitor is kinetic inhibitor alone, ρ is the density of water (kg/m)³) And pi is the circumferential rate, r is the inner diameter (m) of the column, and l is the height (m) of the region affected by the kinetic inhibitor added into the column.

(3) When o is₁＝1,o₂When 1, thermodynamic inhibitor and kinetic force are controlledThe amounts of chemical inhibitors were:

wherein m is_t1Amount of thermodynamic inhibitor in inhibitor (kg), m_d1The amount (kg) of kinetic inhibitor in the inhibitor, and ρ is the density of water (kg/m)³) Where Δ T is the temperature drop (. degree. C.) for forming a hydrate, α is the ratio of the concentration of the thermodynamic inhibitor in the substance to be collected to the concentration of the thermodynamic inhibitor in the aqueous solution, M is the molecular weight (kg/mol) of the thermodynamic inhibitor, K is a constant, and Q is the flow rate (M) of the substance to be collected in the column (M)³) C is the molar concentration (mol/m) of the thermodynamic inhibitor³) And pi is the circumference ratio, r is the inner diameter (m) of the column, and l is the height (m) of the area affected by the inhibitor added into the column.

The method for safely suppressing underwater trees for hydrate suppression in deepwater operation provided by the invention is further described with reference to specific examples.

The downhole operation was simulated, and 16 sets of different temperatures and pressures corresponding to hydrate formation were simulated for testing, the specific data being shown in table 3.

TABLE 3 simulation data

According to the principle of the detection evaluation model established in the foregoing, the addition depth of the inhibitor and the states of the first injection valve and the second injection valve are determined, and the results are shown in table 4.

Table 4 output results

Grouping	First filling valve	Second filling valve	Depth (m) of inhibitor addition
				1	0	1	500
2	0	1	550
				3	0	1	600
4	0	1	650
				5	1	0	700
6	1	0	750
				7	1	0	800
8	1	0	850
				9	1	0	900
10	1	1	950
				11	1	1	1000
12	1	1	1100
				13	1	1	1200
15	1	1	1300
				15	1	1	1400
16	1	1	1500

And the addition of the inhibitor in accordance with the amount of the inhibitor determined above was followed to observe whether or not hydrate was generated, and the results are shown in table 5.

TABLE 5 hydrate formation results

Grouping	Whether or not to form hydrate
		1	Whether or not
2	Whether or not
		3	Whether or not
4	Whether or not
		5	Whether or not
6	Whether or not
		7	Whether or not
8	Whether or not
		9	Whether or not
10	Whether or not
		11	Whether or not
12	Whether or not
		13	Whether or not
15	Whether or not
		15	Whether or not
16	Whether or not

As can be seen from table 5, no hydrate was formed, indicating that this method effectively suppressed the formation of hydrate.

The underwater tree safety inhibition method for hydrate inhibition in deepwater operation disclosed by the invention determines the opening of the first injection valve and the second injection valve and the addition depth of the inhibitor based on the BP neural network, so that the hydrate formation is efficiently inhibited. And the addition amount of a thermodynamic inhibitor and a kinetic inhibitor can be controlled according to the opening state of the first injection valve and the second injection valve, so that the formation of hydrate is effectively inhibited.

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

1. A safety restraining method for underwater trees for hydrate restraint in deepwater operation is characterized in that when the operation is carried out underground, the adding depth of an inhibitor and the states of a first injection valve and a second injection valve are determined based on a BP neural network, and the safety restraining method comprises the following steps:

step 2: determining input layer neuron vector x ═ { x) of three-layer BP neural network₁,x₂,x₃,x₄,x₅,x₆}; wherein x is₁Is the internal temperature, x, of the downhole string₂Is the internal pressure of the tubular string, x₃Is the external temperature, x, of the downhole string₄Is the external temperature, x, of the downhole string₅Is the temperature at the mud surface of the sea bed, x₆The pressure at the mud surface of the seabed is obtained;

and step 3: mapping the input layer neuron vectors to a middle layer, wherein the number of the neurons in the middle layer is m;

step 4: obtaining output layer neuron vector o ═ o₁,o₂,o₃}; wherein o is₁State of the first filling valve, o₂State of the second filling valve, o₃Is the depth of addition of the inhibitor, soThe output layer neuron value is

2. The underwater tree safety suppression method for hydrate suppression in deepwater operation as claimed in claim 1, wherein the number m of intermediate layer nodes satisfies:

3. The underwater tree safety suppression method for hydrate suppression in deepwater operation as claimed in claim 2, wherein the excitation functions of the intermediate layer and the output layer both adopt an S-shaped function f_j(x)＝1/(1+e^-x)。

4. The underwater tree safety suppression method for hydrate suppression in deepwater operation as claimed in claim 1,2 or 3, wherein o is₁＝1,o₂When the content is 0, the amount of the thermodynamic inhibitor is controlled as follows:

wherein m is_t0The amount of the thermodynamic inhibitor when the inhibitor is only the thermodynamic inhibitor, rho is the density of water, Delta T is the temperature drop for forming hydrate, α is the ratio of the concentration of the thermodynamic inhibitor in the substance to be collected to the concentration of the thermodynamic inhibitor in the aqueous solution, M is the molecular weight of the thermodynamic inhibitor, K is a constant, Q is the flow rate of the substance to be collected in the column, C is the molar concentration of the thermodynamic inhibitor, pi is the circumferential ratio, r is the inner diameter of the column, and l is the height of the region in the column affected by the thermodynamic inhibitorAnd (4) degree.

5. The underwater tree safety suppression method for hydrate suppression in deepwater operation as claimed in claim 1,2 or 3, wherein o is₁＝0,o₂When 1, the amount of the kinetic inhibitor is controlled to be:

6. The underwater tree safety suppression method for hydrate suppression in deepwater operation as claimed in claim 1,2 or 3, wherein o is₁＝1,o₂When the ratio is 1, the amount of the thermodynamic inhibitor and the kinetic inhibitor is controlled to be respectively as follows: