A battery state-based internal welding machine control method, device, equipment and medium

Abstract

The present application relates to a kind of based on battery state's internal welding machine control method, device, equipment and medium, the method includes: according to the battery working parameter of internal welding machine, determine the SOC battery state of the battery, according to the task target and task target information of the internal welding machine, determine the load power demand of each power unit of the internal welding machine, according to each the load power demand and the SOC battery state, determine the target torque of the motor corresponding to each the power unit that meets the first constraint condition of pre-set, to control the internal welding machine based on each the target torque corresponding task target is executed.Through the method of the present application, based on the task target and task target information of internal welding machine, the load power demand of each power unit corresponding to internal welding machine when completing task target can be accurately determined, since each target torque determined meets the first constraint condition, then battery damage can be avoided.

Description

Technical Field

[0001] This invention relates to the field of internal welding machine technology, and more specifically, to an internal welding machine control method, device, equipment, and medium based on battery status. Background Technology

[0002] The advantage of integrated energy-powered internal welding machines lies in using a power battery to provide energy for the entire system. Therefore, battery performance has become an important indicator for evaluating the overall quality of integrated energy-powered internal welding machines and a key element in ensuring their performance and quality. Currently, the power load of integrated energy-powered internal welding machines includes: a walking motor with a rated power of 9.6 kW, a cone head attitude adjustment motor with a rated power of 5.1 kW, a hydraulic pump motor with a rated power of 5.0 kW, and an electric welding machine with a welding power of 10 kW. These high-power loads place stringent requirements on the output power performance of the power battery during operation. Existing power batteries on the market, when at low charge levels, can cause excessively high output power, leading to the battery pack's terminal voltage falling below the discharge cutoff voltage. This results in irreversible damage to the battery's internal separator and electrolyte due to over-discharge, accelerating battery aging and preventing the battery from properly storing and releasing electrical energy. Simultaneously, over-discharge can also cause excessive heat generated by internal chemical reactions, leading to battery overheating, triggering thermal runaway reactions, and causing battery expansion, combustion, or even explosion.

[0003] Currently, existing technologies do not specifically research the power batteries for internal welding machines; most research focuses on power batteries in other fields, such as electric vehicles, rail transportation, and submarines. Therefore, there is an urgent need for a control method for internal welding machines based on battery status. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a method, apparatus, equipment and medium for controlling an internal welding machine based on battery status, in order to solve at least one of the above-mentioned technical problems.

[0005] In a first aspect, the technical solution of the present invention to solve the above-mentioned technical problems is as follows: a method for controlling an internal welding machine based on battery status, the method comprising:

[0006] S1, Obtain the battery operating parameters of the battery of the internal welding machine, wherein the battery operating parameters include the battery load voltage;

[0007] S2, Based on the battery operating parameters, determine the SOC battery state of the battery. The SOC battery state represents the remaining power of the battery and includes the current battery SOC.

[0008] S3, Based on the task objective and task objective information of the inner welding machine, determine the load power requirements of each power consumption unit of the inner welding machine, wherein the task objective information is the state parameter corresponding to the inner welding machine when the task objective is completed;

[0009] S4. Based on the power requirements of each load and the SOC battery status, determine the target torque of the motor corresponding to each power-consuming unit that satisfies the preset first constraint condition, so as to control the internal welding machine to perform the corresponding task target based on each target torque. The first constraint condition is that the battery load voltage is not lower than the battery discharge cutoff voltage, and the current battery SOC is not lower than the lower limit of battery SOC.

[0010] The beneficial effects of this invention are: the SOC battery state can be accurately predicted based on the battery operating parameters; based on the task objectives and task objective information of the internal welding machine, the load power requirements of each power-consuming unit corresponding to the completion of the task objective of the internal welding machine can be accurately determined; thus, by combining the load power requirements and the SOC battery state, the task objectives of the internal welding machine can be completed based on the determined target torque of each motor; since the determined target torques satisfy the first constraint condition, battery damage can be avoided.

[0011] Based on the above technical solution, the present invention can be further improved as follows.

[0012] Furthermore, determining the SOC (State of Charge) of the battery based on the aforementioned battery operating parameters includes:

[0013] Obtain the basic battery parameters of the battery;

[0014] The SOC (State of Charge) of the battery is determined based on the battery's basic parameters and operating parameters.

[0015] The advantage of adopting the above-mentioned further solution is that, by combining the battery's basic parameters and the battery's operating parameters, the battery's SOC (State of Charge) can be determined more accurately.

[0016] Furthermore, determining the SOC (State of Charge) of the battery based on the battery's basic parameters and operating parameters includes:

[0017] Based on the battery's basic parameters and operating parameters, the SOC (State of Charge) of the battery is determined using a pre-established SOC estimation model. The SOC estimation model characterizes the correspondence between different battery operating parameters, different battery basic parameters, and different SOC battery states.

[0018] The State of Charge (SOC) estimation model was trained in the following manner:

[0019] Obtain the basic battery parameters of different internal welding machines, as well as the battery operating parameters of each internal welding machine at different times. Each internal welding machine corresponds to a different actual SOC battery state at different times.

[0020] For the same moment, based on the battery basic parameters and battery operating parameters corresponding to each of the internal welding machines at the same moment, the predicted SOC battery state corresponding to each of the internal welding machines is predicted at the next moment at the same moment through the first initial model. The first initial model is a state-space equation based on Kalman filtering.

[0021] The first loss function value is determined based on the actual SOC battery state of each of the internal welding machines and the predicted SOC battery state of each of the internal welding machines;

[0022] If the first loss function value satisfies the preset first termination condition, then the first initial model that satisfies the first termination condition is determined as the State of Charge (SOC) estimation model. If the first loss function value does not satisfy the first termination condition, then the model parameters of the first initial model are adjusted to train the first initial model based on the adjusted parameters until the first loss function value satisfies the first termination condition.

[0023] The beneficial effect of adopting the above-mentioned further scheme is that, based on the state-space equation of Kalman filtering as the first initial model for training, the resulting State of Charge (SOC) estimation model can accurately estimate the SOC of the battery.

[0024] Furthermore, S3 and S4 are obtained based on a pre-trained power load prediction model, which is a power load prediction MPC model.

[0025] The beneficial effect of adopting the above-mentioned further scheme is that, based on the power load prediction MPC model, that is, the model based on the MPC algorithm as the power load prediction model, the target torque can be accurately predicted.

[0026] Furthermore, the above-mentioned determination of the target torque of the motor corresponding to each of the power-consuming units that satisfies the preset first constraint condition based on the power requirements of each load and the SOC battery state includes:

[0027] Based on the power requirements of each load and the SOC battery status, determine the target torque of the motor corresponding to each of the power-consuming units that satisfies the preset first and second constraints.

[0028] The second constraint is that the output torque of each motor of the inner welding machine is not greater than the target maximum torque, and the motor speed of each motor is not greater than the maximum speed of each motor.

[0029] The target maximum torque is the minimum of the first maximum torque and the second maximum torque. The first maximum torque is the maximum torque that satisfies the first constraint condition, and the second maximum torque is the maximum torque obtained based on the motor dynamics model.

[0030] The beneficial effect of adopting the above-mentioned further scheme is that the determined target torque satisfies the first and second constraint conditions, and the optimal torque (target torque) under the current battery operating parameters can be obtained.

[0031] Furthermore, the above-mentioned power load prediction model was trained in the following way:

[0032] Acquire different task objectives, different task objective information, and different actual motor torques;

[0033] For the same moment, based on the respective task objectives and task objective information corresponding to that same moment, the predicted motor speed of each motor at the next moment is predicted by the second initial model.

[0034] Based on the predicted motor speeds of each motor, the predicted motor torques of each motor are determined.

[0035] The second loss function value is determined based on the actual motor torque and the predicted motor torque.

[0036] If the second loss function value satisfies the preset second termination condition, then the second initial model that satisfies the second termination condition is determined as the power load prediction model. If the second loss function value does not satisfy the second termination condition, then the model parameters of the second initial model are adjusted to train the second initial model based on the adjusted parameters until the second loss function value satisfies the second termination condition. The second termination condition includes the first constraint condition and the second constraint condition.

[0037] The beneficial effects of adopting the above-mentioned further scheme are that the predicted motor torque can be derived from the predicted motor speed, and the second termination condition includes the first constraint condition and the second constraint condition during the training of the power load prediction model, which can improve the training accuracy of the model.

[0038] Furthermore, the aforementioned task objectives include walking target speed, hydraulic flow rate, and cone head attitude adjustment target speed, and the task objective information is based on parameters obtained from pressure sensors, slope sensors, and pipeline posture sensors.

[0039] The advantage of adopting the above-mentioned further solutions is that, based on different task objectives and different task objective information, different application scenarios can be met.

[0040] Secondly, in order to solve the above-mentioned technical problems, the present invention also provides an internal welding machine control device based on battery state, the device comprising:

[0041] The acquisition module is used to acquire the battery operating parameters of the battery of the internal welding machine, including the battery load voltage;

[0042] The SOC battery state determination module is used to determine the SOC battery state of the battery based on the battery operating parameters. The SOC battery state represents the remaining power of the battery and includes the current battery SOC.

[0043] The load power requirement determination module is used to determine the load power requirement of each power consumption unit of the internal welding machine based on the task target and task target information of the internal welding machine. The task target information is the state parameter of the internal welding machine when it completes the task target.

[0044] The control module is used to determine the target torque of the motor corresponding to each of the power-consuming units that meets the preset first constraint condition based on the power demand of each load and the SOC battery state, so as to control the internal welding machine to perform the corresponding task target based on each target torque, wherein the first constraint condition is that the battery load voltage is not lower than the battery discharge cutoff voltage and the current battery SOC is not lower than the lower limit of battery SOC.

[0045] Thirdly, in order to solve the above-mentioned technical problems, the present invention also provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the battery state-based internal welding machine control method of the present application.

[0046] Fourthly, in order to solve the above-mentioned technical problems, the present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the battery-state-based internal welding machine control method of the present application.

[0047] Additional aspects and advantages of this application will be set forth in part in the description which follows, and will become apparent from the description or may be learned by practice of this application. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments of the present invention will be briefly introduced below.

[0049] Figure 1A flowchart illustrating an internal welding machine control method based on battery status, provided as an embodiment of the present invention;

[0050] Figure 2 The discharge curves of a single-cell power battery under different output powers are provided in an embodiment of the present invention for an internal welding machine control method based on battery state.

[0051] Figure 3 A flowchart illustrating another method for controlling an internal welding machine based on battery status, provided in one embodiment of the present invention;

[0052] Figure 4 A second-order equivalent circuit model diagram of an example of an internal welding machine control method based on battery state provided in an embodiment of the present invention;

[0053] Figure 5 A schematic diagram illustrating the result of an example of an internal welding machine control method based on battery state provided in an embodiment of the present invention;

[0054] Figure 6 A schematic diagram of the structure of an internal welding machine control device based on battery status, provided in one embodiment of the present invention;

[0055] Figure 7 This is a schematic diagram of the structure of an electronic device provided in one embodiment of the present invention. Detailed Implementation

[0056] The principles and features of the present invention are described below. The examples given are only for explaining the present invention and are not intended to limit the scope of the present invention.

[0057] The technical solution of the present invention and how the technical solution of the present invention solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of the present invention will now be described with reference to the accompanying drawings.

[0058] The solution provided by this invention can be applied to any application scenario that requires control of the internal welding machine based on battery status. The solution provided by this invention can be executed by any electronic device, such as a user's terminal device. This terminal device can be any device capable of installing applications and accessing web pages through those applications, including at least one of the following: smartphones, tablets, laptops, desktop computers, smart speakers, smartwatches, smart TVs, and smart in-vehicle devices.

[0059] This invention provides a possible implementation, such as... Figure 1The diagram shows a flowchart of an internal welding machine control method based on battery state. This method can be executed by any electronic device, such as a terminal device, or jointly executed by a terminal device and a server. For ease of description, the method provided in this embodiment will be described below using a terminal device as the execution subject as an example. Figure 1 The flowchart shown indicates that the method may include the following steps:

[0060] S1, Obtain the battery operating parameters of the battery of the internal welding machine, wherein the battery operating parameters include the battery load voltage;

[0061] S2, Based on the battery operating parameters, determine the SOC battery state of the battery. The SOC battery state represents the remaining power of the battery and includes the current battery SOC.

[0062] S3, Based on the task objective and task objective information of the inner welding machine, determine the load power requirements of each power consumption unit of the inner welding machine, wherein the task objective information is the state parameter corresponding to the inner welding machine when the task objective is completed;

[0063] S4. Based on the power requirements of each load and the SOC battery status, determine the target torque of the motor corresponding to each power-consuming unit that satisfies the preset first constraint condition, so as to control the internal welding machine to perform the corresponding task target based on each target torque. The first constraint condition is that the battery load voltage is not lower than the battery discharge cutoff voltage, and the current battery SOC is not lower than the lower limit of battery SOC.

[0064] Using the method of this invention, the SOC battery state can be accurately predicted based on battery operating parameters. Based on the task objectives and task objective information of the internal welding machine, the load power requirements of each power-consuming unit corresponding to the completion of the task objective of the internal welding machine can be accurately determined. In this way, by combining the load power requirements and the SOC battery state, the task objectives of the internal welding machine can be completed based on the determined target torque of each motor. Since the determined target torques meet the first constraint condition, battery damage can be avoided.

[0065] The following specific embodiments further illustrate the solution of the present invention. In these embodiments, since battery power is generated through internal chemical reactions, this process is easily affected by uncontrollable factors. Furthermore, due to the highly nonlinear characteristics exhibited by the battery, the state of charge (SOC) cannot be directly measured by instruments; it can only be calculated using a battery model. After obtaining the accurate SOC, power allocation to each electrical unit needs to be determined based on the load power requirements. Currently, internal welding machines integrate multiple environmental sensing sensors, including slope and tilt sensors, hydraulic pressure sensors, and pipeline posture measurement sensors. By combining the automated task target list of the internal welding machine (e.g., pipe walking, hydraulic oil pressurization, adjusting the cone head posture to maintain it in the center of the pipeline, etc.) with the data from the above three types of sensors, the power requirements of each electrical unit can be predicted. The calculated SOC, battery terminal voltage, and required power are then combined to derive the target operating torque for the three types of motors.

[0066] For example, when the internal welding machine climbs a slope, the walking motor does work against gravity while maintaining the target torque, increasing power consumption. This may exceed the current battery state (i.e., the battery outputs more current to meet the power demand of the walking motor, causing the battery module terminal voltage to drop and creating a risk of over-discharge). By reducing the walking motor torque, the battery terminal voltage is kept near the discharge cutoff voltage, thus making reasonable use of the battery's full performance while avoiding battery damage. Figure 2 As shown, the battery terminal voltage drops significantly during high-power discharge, and also when the battery's usable capacity is low. Both of these situations carry the risk of over-discharge of the battery.

[0067] To address the aforementioned issues, this example employs an MPC torque control strategy that simultaneously handles battery terminal voltage constraints and future electrical loads within the prediction time domain. Tracking the power consumption of each module of the internal welding machine is used as the objective function. The target load and battery power status are used as input constraints to optimize the target torque parameters. A dynamic programming algorithm is then used to obtain the optimal motor power torque output sequence within the prediction window. This optimization ensures that the battery terminal voltage of the internal welding machine will not fall below the discharge cutoff voltage for a given period, enabling the internal welding machine to proactively reduce torque before performing electrical actions to avoid the risk of battery over-discharge.

[0068] Based on the above, see Figure 3 and Figure 1 The internal welding machine control method based on battery status provided in this embodiment may include the following steps:

[0069] S1, Obtain the battery operating parameters of the battery of the internal welding machine, wherein the battery operating parameters include the battery load voltage;

[0070] Among them, battery operating parameters refer to the parameters of the battery during operation, which may include, but are not limited to, the voltage and current of the battery during charging and discharging, as well as parameters that change over time, such as the battery load voltage (also known as the battery terminal voltage), which refers to the voltage of the battery under load.

[0071] S2, Based on the battery operating parameters, determine the SOC battery state of the battery. The SOC battery state represents the remaining power of the battery and includes the current battery SOC.

[0072] Among them, the current battery SOC refers to the parameter that represents the remaining capacity of the battery at the current moment.

[0073] Optionally, one possible implementation of S2 above is as follows:

[0074] S21, Obtain the basic battery parameters of the battery;

[0075] S22, determine the SOC (State of Charge) of the battery based on the battery's basic parameters and operating parameters.

[0076] Among them, the basic battery parameters refer to the basic parameters of the battery, such as the battery model, the values ​​of each electronic component in the battery's equivalent circuit, and other battery model parameters.

[0077] Optionally, the above battery operating parameters are battery operating parameters at different times, and one possible implementation of S22 is as follows:

[0078] S221, Based on the battery basic parameters and the battery operating parameters at different times, determine the amount of change of the same battery operating parameter at different times;

[0079] S222, determine the SOC (State of Charge) of the battery based on the changes in the same battery operating parameters at different times.

[0080] Optionally, one possible implementation of S22 above is as follows:

[0081] Based on the battery's basic parameters and operating parameters, the SOC (State of Charge) of the battery is determined using a pre-established SOC estimation model. The SOC estimation model characterizes the correspondence between different battery operating parameters, different battery basic parameters, and different SOC states.

[0082] The above S221 and S222 are processing steps completed within the State of Charge (SOC) estimation model.

[0083] The State of Charge (SOC) estimation model is trained in the following manner:

[0084] S110, obtain the basic battery parameters of the batteries of different internal welding machines, as well as the battery operating parameters of each internal welding machine at different times, and each internal welding machine corresponds to a different actual SOC battery state at different times;

[0085] Specifically, battery model parameters can be obtained from the battery's basic parameters based on a pre-built second-order equivalent circuit model of the battery. Battery operating parameters can be obtained through measurement, including but not limited to battery terminal voltage V and current I (also known as battery output current). For example, as shown... Figure 4 As shown, the battery model parameters may include: ohmic internal resistance R0, battery polarization internal resistance R1 and R2, and battery polarization capacitance C1 and C2.

[0086] S120, For the same moment, based on the battery basic parameters and battery operating parameters corresponding to each of the inner welding machines at the same moment, the predicted SOC battery state corresponding to each of the inner welding machines is predicted at the next moment at the same moment through the first initial model. The first initial model is a state-space equation based on Kalman filtering.

[0087] The first initial model includes a first equivalent ohmic resistance model, a second equivalent ohmic resistance model, a covariance model, a discharge polarization voltage state estimation model, a polarization voltage measurement model, a polarization voltage state estimation error model, a polarization parameter optimal state estimation model, and a state of charge (SOC) state and observation model.

[0088] The first equivalent ohmic internal resistance model is used to determine the changes in battery terminal voltage V and battery output current I at two different times, as well as the ohmic internal resistance determined based on the ratio of the changes in battery terminal voltage and battery output current.

[0089] Based on the terminal voltage V and current I of each battery and the second-order equivalent circuit model, a first equivalent ohmic internal resistance model can be constructed. Specifically, the above first equivalent ohmic internal resistance model can be expressed as:

[0090]

[0091] Among them, R o (k) represents the internal resistance in ohms; ΔV represents the change in battery terminal voltage from time k-1 to time k; ΔI represents the change in battery output current from time k-1 to time k; V(k) represents the battery terminal voltage measured at time k; V(k-1) represents the battery terminal voltage measured at time k-1; I(k) represents the battery output current measured at time k; I(k-1) represents the battery output current measured at time k-1; where the unit of resistance is ohms, the unit of voltage is volts, and the unit of current is amperes.

[0092] The second equivalent ohmic resistance model is used to determine the model estimate of the ohmic resistance at two different times based on the changes in battery terminal voltage, battery output current, and ohmic resistance.

[0093] Specifically, a second equivalent ohmic resistance model and a covariance model can be established based on the first equivalent ohmic resistance model. Specifically, the second equivalent ohmic resistance model can be expressed as:

[0094]

[0095] The second equivalent ohmic resistance model can be established using the forgetting factor least squares method.

[0096] in, This is the model estimate of the ohmic internal resistance at time k; P(k) is the model estimate of the ohmic internal resistance at time k-1; P(k) is the covariance at time k (which can be determined by the covariance model); ΔI(k) is the change in battery output current from time k-1 to time k; ΔV(k) is the change in battery terminal voltage from time k-1 to time k.

[0097] The covariance model can be expressed as:

[0098]

[0099] In the above formula, P(k) is the covariance at time k; P(k-1) is the covariance at time k-1; ΔI(k) is the change in battery output current from time k-1 to time k; and a is the forgetting factor constant obtained by cross-validation of the training dataset and the validation dataset, which is a constant.

[0100] The discharge polarization voltage state estimation model is used to determine the polarization voltage (estimated value, also known as polarization voltage estimate) across the battery polarization internal resistances R1 and R2 at time k based on the battery output current at time k-1 and the polarization voltages of R1 and R2 at time k-1.

[0101] Based on the second equivalent ohmic internal resistance model, a discharge polarization voltage state estimation model and a polarization voltage measurement model can be established for the battery polarization internal resistances R1 and R2. The polarization voltage state estimation model can be expressed as:

[0102]

[0103]

[0104] in, V1(k-1) and V2(k-1) are the estimated polarization voltages across the battery polarization resistances R1 and R2 at time k; V1(k-1) and V2(k-1) are the polarization voltages across the battery polarization resistances R1 and R2 at time k-1; ΔT is the time difference from time k-1 to time k; τ1 and τ2 are the two characteristic exponents of the circuit parameters corresponding to R1 and R2, respectively, and are set values; I(k-1) is the battery output current at time k-1; R1 and R2 are the battery polarization resistances; φ1(k) and φ2(k) are the measurement vectors composed of the polarization voltages across R1 and R2 at time k and the battery output current at time k. It is a solution vector consisting of the exponential terms of the general solution of the second-order equivalent circuit model, which includes the polarization resistance and capacitance parameters.

[0105] The polarization voltage measurement model is used to determine the polarization voltage (measured value, also known as polarization voltage measurement value) across the battery polarization internal resistances R1 and R2 at time k based on the battery load output voltage (battery load voltage), battery open circuit voltage, battery output loop current (battery output current) at time k, ohmic internal resistance at time k, and the battery terminal voltage across the polarization internal resistances R1 and R2 at time k.

[0106] The polarization voltage measurement model can be expressed as:

[0107] y1(k)=V oc -V t -I(k)R o (k)-V2(k)

[0108] y2(k)=V oc -V t -I(k)R o (k)-V1(k) (5)

[0109] Where y1(k) and y2(k) are the measured polarization voltages across the polarization internal resistances R1 and R2 at time k, respectively; V oc V t Let I(k) be the battery open-circuit voltage at time k and the battery output voltage under load, respectively; let R be the battery output loop current at time k; o (k) is the ohmic internal resistance at time k obtained above; V1(k) and V2(k) are the battery terminal voltages at time k, representing the polarization internal resistances at both ends of R1 and R2.

[0110] S130, determine the first loss function value based on the actual SOC battery state of each of the internal welding machines and the predicted SOC battery state of each of the internal welding machines;

[0111] S140, if the first loss function value satisfies the preset first termination condition, then the first initial model that satisfies the first termination condition is determined as the State of Charge (SOC) estimation model. If the first loss function value does not satisfy the first termination condition, then the model parameters of the first initial model are adjusted to train the first initial model based on the adjusted parameters until the first loss function value satisfies the first termination condition.

[0112] Optionally, the implementation process of S120 to S140 above can be as follows:

[0113] 1. The polarization voltage state estimation error model can be confirmed based on the polarization voltage state estimation model and the polarization voltage measurement model.

[0114] The above polarization voltage state estimation error model can be expressed as:

[0115]

[0116]

[0117] Where ε1 and ε2 are the estimation errors of the polarization voltage state, i.e. the values ​​of the first loss function; y1(k) and y2(k) are the measured values ​​of the polarization voltage across the polarization internal resistances R1 and R2 at time k, respectively. These are the estimated polarization voltages across the battery polarization internal resistances R1 and R2 at time k, respectively.

[0118] 2. An optimal state estimation model for polarization parameters can be established based on the extended Kalman filter and the polarization voltage state estimation error model.

[0119] The optimal state estimation model for polarization parameters is used to determine the optimal estimates of R1 and R2 and the optimal estimates of battery polarization capacitors C1 and C2 based on the solution vector composed of the exponential terms of the general solution of the second-order equivalent circuit model.

[0120] The optimal state estimation model for polarization parameters can be expressed as:

[0121]

[0122]

[0123] in,

[0124]

[0125] P i (k)=P i (k-1)-K(k)φ i T P i(k-1)+Q RC，i =1,2;

[0126]

[0127] In the above formula, This provides the optimal estimates for R1 and R2. The optimal estimates for C1 and C2; and These are the first and second elements of the solution vector that contain the polarization resistance parameter, respectively. Let K be the estimated values ​​of the i-th polarization resistor and the i-th polarization capacitor at time k-1; i ε is the gain matrix; i For the fitting residuals; K i (k) is the gain matrix at time k; P i (k-1) is the covariance matrix at time k-1; φ i Let φ be the vector formed by the voltage and current across the i-th polarized resistor; i (k) is the vector formed by the voltage and current across the i-th polarized resistor at time k; φ i T For the above φ i Transpose of (k); P i (k) is the covariance matrix at time k; Q RC，i Let y be the state transition noise matrix for the i-th pair of polarization resistors and capacitors; i (k) represents the measured polarization voltage of the i-th polarization voltage at time k; This is the estimated polarization voltage of the i-th pair of polarization resistors at time k; These are the estimated values ​​of the i-th polarization resistance and polarization capacitance parameters at time k.

[0128] 3. Based on the optimal state estimation model of polarization parameters and the extended Kalman filter, a state-of-charge (SOC) state and observation model can be established.

[0129] Among them, the State of Charge (SOC) state and observation model is used to determine the battery's SOC (actual SOC battery state) based on the optimal estimates of R1 and R2 at time k-1, the battery terminal voltage of the polarization internal resistances R1 and R2 at time k, the battery output loop current at time k-1, the battery load voltage at time k, the battery open circuit voltage at time k, the battery ohmic internal resistance at time k, and the battery output loop current at time k.

[0130] The State of Charge (SOC) state and observation model can be expressed as follows:

[0131]

[0132] in,

[0133] In the above formula, SOC represents the battery state of charge, i.e., the actual SOC battery state; V1 and V2 are the battery terminal voltages at time k, corresponding to the polarization resistances R1 and R2; ΔT is the time interval between the two observations; τ1 and τ2 are the two time constants of the equivalent second-order circuit described above; k is the observation time; R1(k-1) and R2(k-1) are the optimal estimates of the two polarization resistances obtained above at time k-1; I(k-1) is the battery loop current at time k-1; V t (k) represents the battery load voltage at time k; V oc R is the battery open-circuit voltage. o (k) is the ohmic internal resistance of the battery at time k obtained above; I(k) is the battery output loop current at time k; Q c This refers to the battery's rated capacity; ω k-1 For predicting noise; v k For observation noise; A is the state transition matrix, representing the transition of the battery state from time k-1 to time k; B is the input matrix, representing the influence of I(k-1) on the battery state parameters; C is the measurement vector, representing the component selected for measurement from the state vector; η k For measuring noise; ΔT is the time difference from time k-1 to time k; τ1 and τ2 are the two characteristic exponents of the circuit parameters.

[0134] 4. The SOC estimation model can be confirmed based on the SOC state and observation model.

[0135] The State of Charge (SOC) estimation model is used to determine the predicted SOC of the battery based on the estimated polarization voltage of R1, the estimated polarization voltage of R2, and the measured polarization voltage across the polarization internal resistances R1 and R2 at time k.

[0136] The State of Charge (SOC) estimation model can be expressed as:

[0137]

[0138] in,

[0139] In the above formula, K k For Kalman gain; ε k P represents the residual between the observed and estimated values. k-1 , P k Let C be the covariance matrix at time k-1, the covariance matrix at time k, and the updated covariance matrix (updated based on the adjusted parameters); C is the measurement vector representing the component selected for measurement from the state vector; C TR is the transpose of C; R is the covariance matrix of the observation noise; A represents the state transition matrix of the battery state (state of charge) from time k-1 to time k. T y is the transpose of the state transition matrix A; k These are the observed values ​​of the battery's operating parameters, namely the measured values ​​of the polarization voltage across the polarization internal resistances R1 and R2 at time k. To predict the SOC (State of Charge) of the battery; This is the first polarization voltage estimate, i.e., the polarization voltage estimate of R1; This is the second polarization voltage estimate, i.e., the polarization voltage estimate of R2.

[0140] S3, Based on the task objective and task objective information of the inner welding machine, determine the load power requirements of each power consumption unit of the inner welding machine, wherein the task objective information is the state parameter corresponding to the inner welding machine when the task objective is completed;

[0141] Among them, load power demand refers to the load power required by each power unit when the internal welding machine completes any task objective.

[0142] Optionally, the above-mentioned task objectives may include walking target speed, hydraulic flow rate, and cone head attitude adjustment target speed. The task objective information is based on parameters obtained from a pressure sensor (which may be a hydraulic pressure sensor), a slope sensor (also known as a slope tilt sensor), and a pipe posture sensor (also known as a pipe attitude measurement sensor).

[0143] Among them, the walking target speed refers to the speed that the inner welding machine needs to reach when moving inside the pipe, corresponding to the task; the hydraulic flow rate speed refers to the speed at which the inner welding machine needs to pressurize the hydraulic oil and reach the required hydraulic flow rate; and the cone head posture adjustment target speed refers to the speed at which the inner welding machine needs to reach the cone head posture adjustment target speed (i.e., adjusting the cone head posture to remain in the center of the pipe; when the cone head posture adjustment target speed is reached, the cone head posture remains in the center of the pipe). Task target information refers to the parameters obtained from different sensors, which correspond to the parameters required to complete different task targets.

[0144] S4. Based on the power requirements of each load and the SOC battery status, determine the target torque of the motor corresponding to each power-consuming unit that satisfies the preset first constraint condition, so as to control the internal welding machine to perform the corresponding task target based on each target torque. The first constraint condition is that the battery load voltage is not lower than the battery discharge cutoff voltage, and the current battery SOC is not lower than the lower limit of battery SOC.

[0145] Optionally, S3 and S4 above are obtained based on a pre-trained power load prediction model, which is a power load prediction MPC model.

[0146] Optionally, in S4 above, determining the target torque of the motor corresponding to each of the power-consuming units that satisfies the preset first constraint condition based on the power demand of each load and the SOC battery state includes:

[0147] S41, based on the power requirements of each load and the SOC battery status, determine the target torque of the motor corresponding to each of the power-consuming units that satisfies the preset first and second constraints;

[0148] The second constraint is that the output torque of each motor of the inner welding machine is not greater than the target maximum torque, and the motor speed of each motor is not greater than the maximum speed of each motor.

[0149] The target maximum torque is the minimum of the first maximum torque and the second maximum torque. The first maximum torque is the maximum torque that satisfies the first constraint condition, and the second maximum torque is the maximum torque obtained based on the motor dynamics model.

[0150] Optionally, the above power load prediction model is trained in the following way:

[0151] S210, acquires different task objectives, different task objective information, and different actual motor torques;

[0152] The aforementioned mission objective information can be obtained based on the different sensors described above.

[0153] S220, For the same moment, based on the task objectives and task objective information corresponding to the same moment, the predicted motor speed of each motor at the next moment is predicted by the second initial model (in this scheme, the system state equation can be selected as the second initial model).

[0154] S230, determine the predicted motor torque of each motor based on the predicted motor speed of each motor;

[0155] S240, determine the second loss function value based on each of the actual motor torques and each of the predicted motor torques;

[0156] S250, if the second loss function value satisfies the preset second termination condition, then the second initial model that satisfies the second termination condition is determined as the power load prediction model. If the second loss function value does not satisfy the second termination condition, then the model parameters of the second initial model are adjusted to train the second initial model based on the adjusted parameters until the second loss function value satisfies the second termination condition. The second termination condition includes the first constraint condition and the second constraint condition.

[0157] The load power demand of each power-consuming unit can be determined based on the predicted motor speed, and therefore the load power demand can be output based on the trained power load prediction model.

[0158] The first constraint and the second constraint mentioned above can be represented by their respective first constraint relationship models and second constraint relationship models, wherein the first constraint relationship model can be represented as:

[0159]

[0160] Among them, SoC min (k) is the lower limit of the battery SOC; SoC(k) is the battery SOC at the current time k, i.e., the current battery SOC; V min This is the discharge cutoff voltage of the battery under load; V t (k) represents the battery load voltage at the current time k.

[0161] The second constraint relationship model can be expressed as:

[0162]

[0163] Among them, T m (k) represents the output torque of a motor at time k; T m，max (k) represents the maximum torque under the motor dynamics model; T b，max (k) represents the maximum torque under the constraints of the battery's SOC lower limit and battery discharge cutoff voltage, i.e., the maximum torque that satisfies the first constraint condition; υ(k) represents the motor speed of a motor at the current time k; υ max (k) represents the maximum speed of the motor.

[0164] Among them, the motor dynamics model is a model in the existing technology, used to output the maximum torque, and how it is implemented will not be elaborated here.

[0165] Optionally, the second initial model described above can be expressed as:

[0166] υ(k)=f(υ(k-1),T m (k-1), P, θ, ψ)(12)

[0167] Where υ(k-1) represents the speed of each motor at time k-1; T m (k-1) represents the output torque of each motor at time k-1; P represents the hydraulic oil pressure output by the pressure sensor; θ represents the walking slope angle output by the slope sensor; ψ represents the cone head attitude deviation degree output by the pipeline posture sensor; υ(k) represents the motor speed of each motor at time k. The unit of hydraulic oil pressure is MPa, the unit of slope angle is degrees, and the unit of cone head deviation degree is degrees.

[0168] Based on the second initial model mentioned above, the motor speed of each motor at time k-1 (for example, time k-1 is the same time), the output torque of each motor at time k-1, and the task target information at time k (the next time after the same time) can be used to predict the motor speed of each motor at time k, i.e., the rotational speed of each predicted motor.

[0169] In this application, after predicting the motor speed of each motor at time k, the predicted motor torque of each motor at the next time (time k) can be determined based on the predicted motor speed.

[0170] Therefore, the loss function determined above based on the actual motor torque and the predicted motor torque of a motor can be expressed as:

[0171]

[0172] Among them, J(T) m ) represents the perfect square difference between the actual motor torque and the reference torque (predicted motor torque) at the desired speed (predicted motor speed at the next moment) of a motor under the above two constraints within the prediction time domain; N is the length of the prediction time domain; is the discrete sequence after discretizing the prediction time; T m (k) represents the actual motor torque; T ref This is the reference torque (predicted motor torque) at the target speed (desired speed).

[0173] Formula (13) above represents the loss function between the actual motor torque and the predicted motor torque of a motor. If there are multiple motors, the second loss function value above is the product of the number of motors and formula (13) above.

[0174] Optionally, in this application, the power load prediction model also incorporates a dynamic programming (DP) algorithm to determine each target torque.

[0175] Specifically, the control torque T can be determined based on the value of the second loss function. m The minimum execution cost of (predicted motor torque) in the forward prediction time domain, and the motor torque corresponding to the minimum value is the optimal execution torque, the target torque.

[0176] The above power load forecasting model can be specifically expressed as follows:

[0177]

[0178] Among them, u opt (k) represents the optimal torque (target torque) at time k; This is the cost of predicting torque loss in the forward time domain.

[0179] As an example, the aforementioned forward prediction time domain is as follows: Figure 5 As shown, the general control process of the internal welding machine control method based on battery state of the present invention using the MPC and DP control system is illustrated: the torque of the motor is adjusted with the lower limit of battery SOC and the battery discharge cut-off voltage as constraints so that the motor speed continuously follows the target speed of the motor.

[0180] Figure 5 The following analysis results can be obtained:

[0181] 1) Past time: The system state variables corresponding to the past time include motor speed, motor torque, and data from various sensors. These will be used in the MPC model predictive control algorithm to calculate the future motor speed in the prediction time domain based on the system dynamic equations.

[0182] 2) Forward prediction time domain: The length of this time domain is a constant obtained by evaluating the modeling accuracy of the actual system dynamic equations and the complexity of the pipeline welding environment. It represents how long the MPC model will calculate the system state in the future, that is, how long the system behavior will be considered.

[0183] 3) Sampling time: i.e., the time series of the discrete system.

[0184] 4) Motor torque: DP dynamic optimization first requires discretizing the system state related to the optimization target quantity and finding the global optimal solution in the discrete state space. Therefore, the optimized motor torque execution sequence is discrete.

[0185] 5) Predicting motor speed: The predicted motor speed (i.e. the task objective) obtained from the above system dynamic equations can be used to calculate the motor torque, which will be used to calculate the loss function.

[0186] Compared with the prior art, the solution of the present invention has the following beneficial effects:

[0187] (1) This invention provides a control method for an internal welding machine based on battery state. The method optimizes the management mode of the internal welding machine according to power demand. It includes accurately estimating the parameters and state of charge of the battery model of the internal welding machine, using the least squares method to identify the battery parameters, using the adaptivity of Kalman filtering to predict the battery state through the state space equation, and then correcting the accurate estimation of the battery state of charge through the observation equation. In this way, it can accurately confirm the battery state of charge (SOC) from the current moment to the forward prediction domain and the battery terminal voltage that changes with time under load torque.

[0188] (2) The present invention adopts a joint control method of model predictive control (MPC) algorithm and dynamic programming (DP) algorithm to control the output power of each power load unit of the internal welding machine. The MPC algorithm predicts the future behavior of the system by combining environmental sensor information and the current state of the system. By establishing multiple constraint equations, the overlapping subproblems and optimal substructure properties of the DP algorithm are used. By solving the subproblems, the solution of the original problem is gradually constructed, and the optimal execution torque of the power load under the current battery state is obtained.

[0189] (3) This invention utilizes a joint optimization framework of MPC and DP to continuously predict, provide feedback, and optimize, thereby achieving continuous distribution of battery output power under safe battery conditions. It also avoids battery voltage instability caused by sudden high-power demands from the hydraulic motor, walking motor, and cone head posture adjustment motor. The battery management system uses the current battery status information to adjust the operating efficiency of the power equipment over time during the automated task flow of the internal welding machine.

[0190] Based on and Figure 1 Using the same principle as the method shown, this embodiment of the invention also provides an internal welding machine control device 20 based on battery status, such as... Figure 6 As shown, the battery-state-based internal welding machine control device 20 may include an acquisition module 210, a SOC battery state determination module 220, a load power demand determination module 230, and a control module 240, wherein:

[0191] The acquisition module 210 is used to acquire the battery operating parameters of the battery of the internal welding machine, the battery operating parameters including the battery load voltage;

[0192] SOC battery state determination module 220 is used to determine the SOC battery state of the battery according to the battery operating parameters. The SOC battery state represents the remaining power of the battery and includes the current battery SOC.

[0193] The load power requirement determination module 230 is used to determine the load power requirement of each power consumption unit of the inner welding machine based on the task target and task target information of the inner welding machine. The task target information is the state parameters of the inner welding machine when it completes the task target.

[0194] The control module 240 is used to determine the target torque of the motor corresponding to each of the power-consuming units that meets the preset first constraint condition based on the power demand of each load and the SOC battery state, so as to control the internal welding machine to perform the corresponding task target based on each of the target torques, wherein the first constraint condition is that the battery load voltage is not lower than the battery discharge cutoff voltage and the current battery SOC is not lower than the lower limit of battery SOC.

[0195] Optionally, when determining the SOC battery state based on the battery operating parameters, the aforementioned SOC battery state determination module 220 is specifically used for:

[0196] Obtain the basic battery parameters of the battery;

[0197] The SOC (State of Charge) of the battery is determined based on the battery's basic parameters and operating parameters.

[0198] Optionally, when determining the SOC battery state determination module 220 based on the battery's basic parameters and operating parameters, it is specifically used for:

[0199] Based on the battery's basic parameters and operating parameters, the SOC (State of Charge) of the battery is determined using a pre-established SOC estimation model. The SOC estimation model characterizes the correspondence between different battery operating parameters, different battery basic parameters, and different SOC battery states.

[0200] The State of Charge (SOC) estimation model was trained in the following manner:

[0201] Obtain the basic battery parameters of different internal welding machines, as well as the battery operating parameters of each internal welding machine at different times. Each internal welding machine corresponds to a different actual SOC battery state at different times.

[0202] For the same moment, based on the battery basic parameters and battery operating parameters corresponding to each of the internal welding machines at the same moment, the predicted SOC battery state corresponding to each of the internal welding machines is predicted at the next moment at the same moment through the first initial model. The first initial model is a state-space equation based on Kalman filtering.

[0203] The first loss function value is determined based on the actual SOC battery state of each of the internal welding machines and the predicted SOC battery state of each of the internal welding machines;

[0204] If the first loss function value satisfies the preset first termination condition, then the first initial model that satisfies the first termination condition is determined as the State of Charge (SOC) estimation model. If the first loss function value does not satisfy the first termination condition, then the model parameters of the first initial model are adjusted to train the first initial model based on the adjusted parameters until the first loss function value satisfies the first termination condition.

[0205] Optionally, the processing of the load power demand determination module 230 and the control module 240 is based on a pre-trained power load prediction model, which is a power load prediction MPC model.

[0206] Optionally, when the control module 240 determines the target torque of the motor corresponding to each of the power-consuming units that meets the preset first constraint condition based on the power requirements of each load and the SOC battery state, it is specifically used for:

[0207] Based on the power requirements of each load and the SOC battery status, determine the target torque of the motor corresponding to each of the power-consuming units that satisfies the preset first and second constraints.

[0208] The second constraint is that the output torque of each motor of the inner welding machine is not greater than the target maximum torque, and the motor speed of each motor is not greater than the maximum speed of each motor.

[0209] The target maximum torque is the minimum of the first maximum torque and the second maximum torque. The first maximum torque is the maximum torque that satisfies the first constraint condition, and the second maximum torque is the maximum torque obtained based on the motor dynamics model.

[0210] Optionally, the above power load prediction model is trained in the following way:

[0211] Acquire different task objectives, different task objective information, and different actual motor torques;

[0212] For the same moment, based on the respective task objectives and task objective information corresponding to that same moment, the predicted motor speed of each motor at the next moment is predicted by the second initial model.

[0213] Based on the predicted motor speeds of each motor, the predicted motor torques of each motor are determined.

[0214] The second loss function value is determined based on the actual motor torque and the predicted motor torque.

[0215] If the second loss function value satisfies the preset second termination condition, then the second initial model that satisfies the second termination condition is determined as the power load prediction model. If the second loss function value does not satisfy the second termination condition, then the model parameters of the second initial model are adjusted to train the second initial model based on the adjusted parameters until the second loss function value satisfies the second termination condition. The second termination condition includes the first constraint condition and the second constraint condition.

[0216] Optionally, the task objectives include walking target speed, hydraulic flow rate, and cone head attitude adjustment target speed, and the task objective information is based on parameters obtained from pressure sensors, slope sensors, and pipe position sensors.

[0217] The battery-state-based internal welding machine control device of this invention can execute the battery-state-based internal welding machine control method provided in this invention. The implementation principle is similar. The actions performed by each module and unit in the battery-state-based internal welding machine control device in each embodiment of this invention correspond to the steps in the battery-state-based internal welding machine control method in each embodiment of this invention. For detailed functional descriptions of each module of the battery-state-based internal welding machine control device, please refer to the descriptions in the corresponding battery-state-based internal welding machine control methods shown above, which will not be repeated here.

[0218] The aforementioned battery-state-based internal welding machine control device can be a computer program (including program code) running on a computer device, such as an application software; the device can be used to execute the corresponding steps in the method provided in the embodiments of the present invention.

[0219] In some embodiments, the battery-state-based internal welding machine control device provided in this invention can be implemented using a combination of hardware and software. As an example, the battery-state-based internal welding machine control device provided in this invention can be a processor in the form of a hardware decoding processor, which is programmed to execute the battery-state-based internal welding machine control method provided in this invention. For example, the processor in the form of a hardware decoding processor can be one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), or other electronic components.

[0220] In other embodiments, the battery-state-based internal welding machine control device provided in this invention can be implemented in software. Figure 6 An internal welding machine control device based on battery status, stored in a memory, is shown. It can be software in the form of programs and plug-ins, and includes a series of modules, including an acquisition module 210, a SOC battery status determination module 220, a load power demand determination module 230, and a control module 240, for implementing the internal welding machine control method based on battery status provided in the embodiments of the present invention.

[0221] The modules described in the embodiments of the present invention can be implemented in software or hardware. The names of the modules are not, in some cases, limiting the scope of the module itself.

[0222] Based on the same principles as the methods shown in the embodiments of the present invention, the embodiments of the present invention also provide an electronic device, which may include, but is not limited to: a processor and a memory; the memory for storing computer programs; and the processor for executing the methods shown in any embodiment of the present invention by invoking the computer programs.

[0223] In one alternative embodiment, an electronic device is provided, such as Figure 7 As shown, Figure 7The illustrated electronic device 4000 includes a processor 4001 and a memory 4003. The processor 4001 and the memory 4003 are connected, for example, via a bus 4002. Optionally, the electronic device 4000 may further include a transceiver 4004, which can be used for data interaction between the electronic device and other electronic devices, such as sending and / or receiving data. It should be noted that in practical applications, the transceiver 4004 is not limited to one type, and the structure of the electronic device 4000 does not constitute a limitation on the embodiments of the present invention.

[0224] Processor 4001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this invention. Processor 4001 may also be a combination that implements computational functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0225] Bus 4002 may include a pathway for transmitting information between the aforementioned components. Bus 4002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 4002 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 7 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0226] The memory 4003 may be ROM (Read Only Memory) or other types of static storage devices capable of storing static information and instructions, RAM (Random Access Memory) or other types of dynamic storage devices capable of storing information and instructions, or EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto.

[0227] The memory 4003 stores the application code (computer program) for executing the present invention, and its execution is controlled by the processor 4001. The processor 4001 executes the application code stored in the memory 4003 to implement the content shown in the foregoing method embodiments.

[0228] Among these, electronic devices can also be terminal devices. Figure 7 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0229] This invention provides a computer-readable storage medium storing a computer program that, when run on a computer, enables the computer to execute the corresponding content in the aforementioned method embodiments.

[0230] According to another aspect of the present invention, a computer program product or computer program is also provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the methods provided in the various embodiments described above.

[0231] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. These programming languages ​​include object-oriented programming languages—such as Java, Smalltalk, and C++—and conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0232] It should be understood that the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of methods and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0233] The computer-readable storage medium provided in this invention can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0234] The aforementioned computer-readable storage medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to perform the method shown in the above embodiments.

[0235] The above description is merely a preferred embodiment of the present invention and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of disclosure in this invention is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this invention.

Claims

1. A method for controlling an internal welding machine based on battery status, characterized in that, Includes the following steps: S1, Obtain the battery operating parameters of the battery of the internal welding machine, wherein the battery operating parameters include the battery load voltage; S2, Based on the battery operating parameters, determine the SOC battery state of the battery. The SOC battery state represents the remaining power of the battery and includes the current battery SOC. S3, Based on the task objective and task objective information of the inner welding machine, determine the load power requirements of each power consumption unit of the inner welding machine, wherein the task objective information is the state parameter corresponding to the inner welding machine when the task objective is completed; S4. Based on the power requirements of each load and the SOC battery status, determine the target torque of the motor corresponding to each power-consuming unit that satisfies the preset first constraint condition, so as to control the internal welding machine to perform the corresponding task target based on each target torque. The first constraint condition is that the battery load voltage is not lower than the battery discharge cutoff voltage, and the current battery SOC is not lower than the lower limit of battery SOC.

2. The method according to claim 1, characterized in that, Determining the SOC (State of Charge) of the battery based on the battery operating parameters includes: Obtain the basic battery parameters of the battery; The SOC (State of Charge) of the battery is determined based on the battery's basic parameters and operating parameters.

3. The method according to claim 2, characterized in that, Determining the SOC (State of Charge) of the battery based on the battery's basic parameters and operating parameters includes: Based on the battery's basic parameters and operating parameters, the SOC (State of Charge) of the battery is determined using a pre-established SOC estimation model. The SOC estimation model characterizes the correspondence between different battery operating parameters, different battery basic parameters, and different SOC battery states. The State of Charge (SOC) estimation model was trained in the following manner: Obtain the basic battery parameters of different internal welding machines, as well as the battery operating parameters of each internal welding machine at different times. Each internal welding machine corresponds to a different actual SOC battery state at different times. For the same moment, based on the battery basic parameters and battery operating parameters corresponding to each of the internal welding machines at the same moment, the predicted SOC battery state corresponding to each of the internal welding machines is predicted at the next moment at the same moment through the first initial model. The first initial model is a state-space equation based on Kalman filtering. The first loss function value is determined based on the actual SOC battery state of each of the internal welding machines and the predicted SOC battery state of each of the internal welding machines; If the first loss function value satisfies the preset first termination condition, then the first initial model that satisfies the first termination condition is determined as the State of Charge (SOC) estimation model. If the first loss function value does not satisfy the first termination condition, then the model parameters of the first initial model are adjusted to train the first initial model based on the adjusted parameters until the first loss function value satisfies the first termination condition.

4. The method according to any one of claims 1 to 3, characterized in that, S3 and S4 are obtained based on a pre-trained power load prediction model, which is a power load prediction MPC model.

5. The method according to claim 4, characterized in that, The step of determining the target torque of the motor corresponding to each of the power-consuming units that satisfies the preset first constraint condition based on the power demand of each load and the SOC battery state includes: Based on the power requirements of each load and the SOC battery status, determine the target torque of the motor corresponding to each of the power-consuming units that satisfies the preset first and second constraints. The second constraint is that the output torque of each motor of the inner welding machine is not greater than the target maximum torque, and the motor speed of each motor is not greater than the maximum speed of each motor. The target maximum torque is the minimum of the first maximum torque and the second maximum torque. The first maximum torque is the maximum torque that satisfies the first constraint condition, and the second maximum torque is the maximum torque obtained based on the motor dynamics model.

6. The method according to claim 5, characterized in that, The power load prediction model was trained using the following method: Acquire different task objectives, different task objective information, and different actual motor torques; For the same moment, based on the respective task objectives and task objective information corresponding to that same moment, the predicted motor speed of each motor at the next moment is predicted by the second initial model. Based on the predicted motor speeds of each motor, the predicted motor torques of each motor are determined. The second loss function value is determined based on the actual motor torque and the predicted motor torque. If the second loss function value satisfies the preset second termination condition, then the second initial model that satisfies the second termination condition is determined as the power load prediction model. If the second loss function value does not satisfy the second termination condition, then the model parameters of the second initial model are adjusted to train the second initial model based on the adjusted parameters until the second loss function value satisfies the second termination condition. The second termination condition includes the first constraint condition and the second constraint condition.

7. The method according to any one of claims 1 to 3, characterized in that, The task objectives include walking target speed, hydraulic flow rate, and cone head attitude adjustment target speed. The task objective information is based on parameters obtained from pressure sensors, slope sensors, and pipeline posture sensors.

8. A control device for an internal welding machine based on battery status, characterized in that, include: The acquisition module is used to acquire the battery operating parameters of the battery of the internal welding machine, including the battery load voltage; The SOC battery state determination module is used to determine the SOC battery state of the battery based on the battery operating parameters. The SOC battery state represents the remaining power of the battery and includes the current battery SOC. The load power requirement determination module is used to determine the load power requirement of each power consumption unit of the internal welding machine based on the task target and task target information of the internal welding machine. The task target information is the state parameter of the internal welding machine when it completes the task target. The control module is used to determine the target torque of the motor corresponding to each of the power-consuming units that meets the preset first constraint condition based on the power demand of each load and the SOC battery state, so as to control the internal welding machine to perform the corresponding task target based on each target torque, wherein the first constraint condition is that the battery load voltage is not lower than the battery discharge cutoff voltage and the current battery SOC is not lower than the lower limit of battery SOC.

9. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the method of any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method of any one of claims 1-7.

Images