Multi-parameter adjustment and fault pre-diagnosis screw pump remote control system

Abstract

The invention discloses a screw pump remote control system for multi-parameter adjustment and fault pre-diagnosis, relates to the technical field of operation monitoring, and is used for solving the problems of insufficient prediction precision and poor reliability caused by the fact that the driving capability is not matched with pump body parameters and the requirements of an underground direct-drive system on accurate matching and dynamic monitoring of pump body performance are difficult to meet. In order to solve the problem of monitoring range adjustment lag in the prior art, multi-dimensional data in the operation process of the screw pump are collected, key characteristic values, symmetry information, axis offset and surface wear degree are extracted, a key monitoring area is determined, a stability index is calculated, and an index regression algorithm is utilized to calculate a dynamic adjustment coefficient so as to set an initial monitoring range. The operation quality type is evaluated through a double-threshold mechanism, the distance between the working temperature and the key position is collected in the medium and poor state, the feature vector is constructed to be input into the support vector regression model, the monitoring range is dynamically adjusted, intelligent recognition and optimal control over the operation state are achieved, and the equipment stability and prediction capacity are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of operation monitoring. More specifically, the present invention relates to a remote control system for a screw pump with multi-parameter adjustment and fault pre-diagnosis. Background Art

[0002] Due to its strong adaptability and high-efficiency transportation ability, screw pumps are widely used in oil production scenarios with complex downhole conditions such as high-viscosity crude oil, high sand content, and multiphase flow. Traditional screw pumps are mostly driven by surface drive devices through sucker rod systems to drive the downhole pump head to operate. Although the surface motor has sufficient power, limited by the long torque transmission path and the mechanical limit of the sucker rod, the rotational speed of the screw pump is usually controlled between 70 and 150 rpm. Under the design of high interference fit (0.1 to 0.3 mm), the swelling of the rubber stator caused by the downhole temperature further increases the frictional torque between the rotor and the stator, resulting in periodic bending of the sucker rod, aggravated rod-tube wear, and in severe cases, pump body jamming, inability to start, and other faults.

[0003] With the development of electric submersible pump technology, especially the electric submersible screw pump system with downhole motor direct drive, the mechanical degradation problem of the rod-tube system can be effectively avoided, and it has the advantages of energy saving, environmental protection, and long maintenance cycle. However, problems such as frequent startup failures and abnormal torque loads of screw pumps still occur frequently during field applications. The root cause is that the performance test of the screw pump before being lowered into the well fails to fully reflect its operating characteristics under actual high-temperature and high-pressure conditions, resulting in a mismatch between the driving ability and the pump body parameters.

[0004] During the field application of the prior art, problems such as frequent startup failures and abnormal torque loads of screw pumps still occur frequently. The root cause is that the performance test of the screw pump before being lowered into the well fails to fully reflect its operating characteristics under actual high-temperature and high-pressure conditions, resulting in a mismatch between the driving ability and the pump body parameters, making it difficult to meet the requirements of the downhole direct drive system for precise matching and dynamic monitoring of the pump body performance, lacking a mechanism for mining historical operation data and pattern recognition, resulting in insufficient prediction accuracy and lag in monitoring range adjustment. Therefore, a remote control system for a screw pump with multi-parameter adjustment and fault pre-diagnosis is proposed.

[0005] The above information disclosed in the background art section is only used to enhance the understanding of the background of the present disclosure. Therefore, it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0006] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a remote control system for a screw pump with multi-parameter adjustment and fault pre-diagnosis. By introducing symmetry analysis, dynamic exponential regression, and support vector machine prediction mechanisms, dynamic monitoring and optimized evaluation of the multi-dimensional operating state of the screw pump are realized to solve the problems proposed in the above background art.

[0007] To achieve the above object, the present invention provides the following technical solution. A remote control system for a screw pump with multi-parameter adjustment and fault pre-diagnosis includes a data acquisition module, a device identification module, a quality assessment module, and a monitoring and optimization module; The data acquisition module is used to collect multi-dimensional data on the operating state of the screw pump and extract key characteristic values, obtain the symmetry information of the screw pump, transmit the key characteristic values and symmetry information to the device identification module. After receiving the screw pump mark passed in by the device identification module, it obtains the axial center offset and surface wear degree of the screw pump and transmits them back to the device identification module. After receiving the screw pump operation quality type passed in by the quality assessment module, it collects the working temperature and the distance between key positions of the screw pump and sends them to the monitoring and optimization module; The device identification module determines multiple key monitoring areas in the operating state of the screw pump according to the key characteristic values in the multi-dimensional data, calculates the stability index of the screw pump according to the symmetry information, and sets the screw pump mark to be transmitted to the data acquisition module; after receiving the axial center offset of the screw pump, it calculates the offset amplitude, comprehensively uses the received surface wear degree and offset amplitude to calculate the dynamic adjustment coefficient by using the exponential regression algorithm, combines the stability index of the screw pump and the dynamic adjustment coefficient to determine the monitoring range of each key monitoring area, and transmits the monitoring range to the quality assessment module; The quality assessment module receives the monitoring range passed in by the device identification module, sets the monitoring threshold, compares each key monitoring area with the monitoring threshold to evaluate the screw pump operation quality type, and transmits the monitoring range to the monitoring and optimization module; it sends the screw pump operation quality type to the data acquisition module and the monitoring and optimization module; The monitoring and optimization module selects the monitoring range adjustment mode according to the screw pump operation quality type, and re-evaluates the monitoring range by using the support vector machine regression algorithm in combination with the working temperature and the distance between key positions.

[0008] In a preferred embodiment, a preset acquisition period is evenly divided into multiple acquisition moments, and the acceleration values and pressure values of different components of the screw pump are obtained; The acceleration values of the same component at each acquisition moment are comprehensively calculated to obtain the vibration amplitude; The absolute value of the difference between the pressure values at the inlet end and the outlet end of different components in the screw pump sealing structure is taken to obtain the pressure deviation; The three-dimensional model of the screw pump is obtained, a vertical section is constructed based on the main axis of the three-dimensional model, the three-dimensional model is divided into two symmetrical parts, and the structural volumes on both sides of the vertical section are obtained as symmetry information.

[0009] In a preferred embodiment, after receiving the screw pump mark, the axial center coordinates during the operation of the screw pump are obtained, and the main axis is evenly divided into multiple vertical cross-sections along the main axis direction; Calculate the distance between the centroid coordinates of each cross-section and the centroid coordinates of the corresponding cross-section in the non-operating state as the axial offset of the screw pump; Obtain the height at different coordinates through the 3D model of the screw pump, and calculate the wear depth by taking the difference from the height at the corresponding coordinates in the non-operating state; Calculate the surface wear degree of each component through area integration for each wear depth; Obtain the boundary coordinates of the key monitoring area, calculate the Euclidean distance from multiple adjacent key monitoring areas, and take the minimum value of the Euclidean distance as the key position spacing; Collect the working temperatures in different areas during the operation of the screw pump, and take the average value as the working temperature of the screw pump.

[0010] In a preferred embodiment, preset an amplitude threshold and a deviation threshold, and compare them with the vibration amplitude and pressure deviation respectively to determine the key monitoring area: If the vibration amplitude is greater than the amplitude threshold, or the pressure deviation is greater than the deviation threshold, the corresponding part is judged as the key monitoring area; If the vibration amplitude is less than or equal to the amplitude threshold, and the pressure deviation is less than or equal to the deviation threshold, the corresponding part is judged as a non-key monitoring area; Calculate the stability index based on the symmetry information; If there is a key monitoring area in the screw pump, number and mark the components in the key monitoring area.

[0011] In a preferred embodiment, calculate the offset amplitude through the axial offset of the screw pump; After normalizing the surface wear degree and the offset amplitude respectively, calculate the dynamic adjustment coefficient through the exponential regression algorithm; Associate and calculate the stability index with the position of the components in the key monitoring area to obtain the stability index of different key monitoring areas; Normalize the stability index of the key monitoring area and the dynamic adjustment coefficient, and calculate the monitoring range through a non-linear function.

[0012] In a preferred embodiment, preset a first monitoring threshold and a second monitoring threshold, and ensure that the first monitoring threshold is less than the second monitoring threshold; If the monitoring range is less than or equal to the first monitoring threshold, it is determined that the operation quality type of the screw pump is excellent; If the monitoring range is greater than the first monitoring threshold and less than or equal to the second monitoring threshold, it is determined that the operation quality type of the screw pump is medium; If the monitoring range is greater than the second monitoring threshold, it is determined that the operation quality type of the screw pump is poor.

[0013] In a preferred embodiment, collect the working temperature; Calculate the minimum Euclidean distance between the center point of the current key monitoring area and the center points of multiple adjacent key monitoring areas to obtain the key position spacing; Select a monitoring range adjustment mode according to the operation quality type; If the operation quality type is excellent, select the monitoring range adjustment mode as the maintenance mode; If the operation quality type is medium, select the monitoring range adjustment mode as the contraction mode; If the operation quality type is poor, select the monitoring range adjustment mode as the key optimization mode.

[0014] In a preferred embodiment, in the maintenance mode, no adjustment operation is performed; In the contraction mode, construct the monitoring range, working temperature, and key position spacing into a contraction feature vector; Input the contraction feature vector as an input into the support vector regression model for the contraction mode that has been trained with historical operation data; The support vector regression model for the contraction mode uses a radial basis kernel function to achieve non - linear mapping and outputs the proportional coefficient by which the monitoring range needs to be reduced; Calculate the difference between the monitoring range multiplied by one and the proportional coefficient by which the monitoring range needs to be reduced to obtain the adjusted monitoring range in the contraction mode.

[0015] In a preferred embodiment, in the key optimization mode, construct the monitoring range, working temperature, and key position spacing into an optimization feature vector; Input the optimization feature vector into the support vector regression model for the optimization mode; The support vector regression model for the optimization mode is trained based on a non - linear kernel function and historical key fault area samples and outputs the target contraction ratio; Introduce a joint risk correction value for the working temperature and key position spacing, and the calculation formula is ; where, is the empirical risk adjustment factor, is the working temperature, is the maximum working temperature, is a small positive constant; Calculate the difference between the monitoring range multiplied by one and the product of the target contraction ratio and the joint risk correction value to obtain the adjusted monitoring range in the key optimization mode.

[0016] The technical effects and advantages of the present invention: 1. The present invention collects multi-dimensional data during the operation of a screw pump, extracts key characteristic values and symmetry information, obtains the shaft center offset and surface wear degree, determines multiple key monitoring areas based on the key characteristic values, calculates a stability index in combination with the symmetry information, and uses an exponential regression algorithm to calculate a dynamic adjustment coefficient based on the wear degree and offset amplitude, so as to determine the initial monitoring range of each key monitoring area, set a dual-threshold mechanism, determine the operation quality type as excellent, medium or poor according to the comparison result of each area and the threshold, set a corresponding monitoring range adjustment mode according to the operation quality type, collect the working temperature and the distance between key positions under the medium and poor types, construct a feature vector and input it into a support vector regression model to achieve the adaptive adjustment of the monitoring range. Through multi-parameter fusion, the accurate determination and efficient optimization of the operation quality of the screw pump are realized, and the operation stability and intelligent level of the equipment are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a structural framework diagram of a remote control system for a screw pump with multi-parameter adjustment and fault pre-diagnosis according to the present invention.

[0018] Figure 2 It is an implementation flowchart of a remote control system for a screw pump with multi-parameter adjustment and fault pre-diagnosis according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0019] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention. Embodiment

[0020] A remote control system for a screw pump with multi-parameter adjustment and fault pre-diagnosis, as Figures 1 to 2 shown, includes a data acquisition module, an equipment identification module, a quality assessment module, and a monitoring and optimization module. Data interaction is realized through signal connection between each module; The functions of each module are as follows: The data acquisition module is used to collect multi-dimensional data of the operation state of the screw pump and extract key characteristic values, obtain the symmetry information of the screw pump, transmit the key characteristic values and symmetry information to the equipment identification module, obtain the shaft center offset and surface wear degree of the screw pump after receiving the screw pump mark passed in by the equipment identification module and transmit it back to the equipment identification module, and collect the working temperature and the distance between key positions of the screw pump and send them to the monitoring and optimization module after receiving the operation quality type of the screw pump passed in by the quality assessment module; The device recognition module determines multiple key monitoring areas in the operation state of the screw pump according to the key feature values in the multi-dimensional data, calculates the stability index of the screw pump according to the symmetry information, and sets the screw pump mark to be transmitted to the data acquisition module; after receiving the axial offset of the screw pump, it calculates the offset amplitude, comprehensively uses the exponential regression algorithm to calculate the dynamic adjustment coefficient based on the received surface wear degree and offset amplitude, combines the stability index of the screw pump and the dynamic adjustment coefficient to determine the monitoring range of each key monitoring area, and transmits the monitoring range to the quality assessment module; The quality assessment module receives the monitoring range transmitted by the device recognition module, sets the monitoring threshold, compares the monitoring range with the monitoring threshold to evaluate the operation quality type of the screw pump, and transmits the monitoring range to the monitoring and optimization module; it sends the operation quality type of the screw pump to the data acquisition module and the monitoring and optimization module; The monitoring and optimization module selects the monitoring range adjustment mode according to the operation quality type of the screw pump, and re-evaluates the monitoring range by using the support vector machine regression algorithm in combination with the working temperature and the distance between key positions.

[0021] The specific implementation is as follows: As a positive displacement pump, the basic structure of the screw pump is composed of a metal screw rotor meshing with an elastic stator (such as a fluororubber inner cavity) to form a sealed cavity. When the rotor rotates, the medium is continuously conveyed; further, the single screw pump is a common form, the rotor is spiral and rotates eccentrically along the stator cavity, and the pump body is axially installed underground or on the ground, and is directly driven by mechanical drive or motor.

[0022] In the data acquisition module, a preset acquisition period is evenly divided into multiple acquisition times, and the acceleration values and pressure values of different components of different screw pumps at the acquisition times are respectively detected by an acceleration sensor and a pressure sensor; Square the acceleration values of the same component at each acquisition time, take the average of all squares and then take the square root to obtain the vibration amplitude; Record the pressure values at the inlet end and outlet end of different components in the screw pump sealing structure, and take the mean difference and absolute value of the pressure values at the inlet end and outlet end at each acquisition time to obtain the pressure deviation; Transmit the vibration amplitude and pressure deviation as key feature values to the device recognition module for subsequent screening of key monitoring areas by the device recognition module; Obtain the three-dimensional model of the screw pump through a three-dimensional laser scanner, construct a vertical section based on the main axis of the three-dimensional model, divide the three-dimensional model into two symmetrical parts, and obtain the structural volumes on both sides of the vertical section through three-dimensional modeling software; Transmit the structural volumes on both sides of the vertical section as symmetry information to the device recognition module for calculating the stability index of the screw pump; After receiving the screw pump mark passed in by the device recognition module, obtain the axial offset of the screw pump and the surface wear degree of the corresponding numbered components; Collect the axial coordinates during operation through a three-dimensional laser scanner, evenly divide the main axis into multiple perpendicular cross-sections along the main axis of the screw pump, and calculate the distance between the coordinates of the centroid of the cross-section and the coordinates of the centroid of the corresponding cross-section in the non-operating state: , where and are the coordinates of the centroid of the i-th cross-section, and are the coordinates of the i-th centroid in the initial axis trajectory, is the axial offset of the i-th screw pump; It should be noted that the coordinates of the centroid are the weighted average of the coordinates within the corresponding cross-section or are calculated by geometric methods, which are specifically set by professionals and will not be elaborated here.

[0023] Obtain the height at different coordinates through the three-dimensional model of the screw pump, subtract the height at the corresponding coordinates in the non-operating state to obtain the wear depth, and calculate the surface wear degree of each component through area integration: , where is the projected area of each component in the two-dimensional plane, is the coordinate is the wear depth at the coordinate, is the surface wear degree; Transmit the axial offset of the screw pump and the surface wear degree to the device recognition module for subsequent calculation of the offset amplitude and dynamic adjustment coefficient; After receiving the screw pump operation quality type passed in by the quality assessment module, collect the working temperature of the screw pump and the distance between key positions; Obtain the boundary coordinates of the key monitoring area through a three-dimensional laser scanner, calculate the Euclidean distance from the key monitoring area to multiple adjacent key monitoring areas, and take the minimum value of the Euclidean distance as the distance between key positions; Collect the working temperatures of different areas during the operation of the screw pump through distributed temperature sensors and take the average value as the working temperature of the screw pump; It should be noted that an acceleration sensor is an electronic sensor device used to measure the acceleration of an object, which can sense the acceleration, deceleration, vibration or shock generated during the movement of the object and convert this physical motion signal into a processable electrical signal; a pressure sensor is a core detection element used to measure the pressure of a liquid or gas, which converts the physical quantity of pressure into an output electrical signal to realize the real-time monitoring, recording and analysis of pressure; a 3D laser scanner is a spatial information acquisition device based on the principle of laser ranging. By emitting laser beams at a high frequency and measuring the reflected echoes, the spatial coordinates of each point on the surface of the target object are obtained, thereby constructing a complete point cloud model of the object; 3D modeling software is a professional software tool used to reconstruct the acquired spatial point cloud model into a complete three-dimensional structure model, and the structural volume on both sides of the vertical section can be obtained through the built-in volume algorithm.

[0024] The device identification module determines multiple key monitoring areas in the operating state of the screw pump according to the key feature values transmitted by the data acquisition module. Preset amplitude threshold and deviation threshold, and compare them with the vibration amplitude and pressure deviation respectively to determine the key monitoring area: If the vibration amplitude is greater than the amplitude threshold, or the pressure deviation is greater than the deviation threshold, the corresponding part is judged as a key monitoring area; If the vibration amplitude is less than or equal to the amplitude threshold, and the pressure deviation is less than or equal to the deviation threshold, the corresponding part is judged as a non-key monitoring area; Calculate the stability index according to the symmetry information: , where is the volume of the left part of the section, is the volume of the right part of the section, is the stability index; The stability index reflects the steady-state level of the operation of the screw pump structure. The larger the stability index, the more deviated the symmetry of the two sides of the structure; If there is a key monitoring area in the screw pump, the components in the key monitoring area are numbered and marked and transmitted to the data acquisition system for obtaining the axial offset of the screw pump and the surface wear degree of the screw pump; Calculate the offset amplitude through the axial offset of the screw pump: , where N is the total number of axial offsets of the screw pump, and O is the offset amplitude; After normalizing the surface wear degree and the offset amplitude respectively, calculate the dynamic adjustment coefficient through the exponential regression algorithm: , where and are preset weight coefficients, is the dynamic adjustment coefficient of the corresponding component; It should be noted that the preset weight coefficient can be obtained through non-linear regression fitting methods. For example, by collecting multiple historical data samples, including the surface wear degree, offset amplitude, and actual dynamic adjustment coefficient of the screw pump, the weight coefficient is obtained by fitting the loss function using the least squares method. Specifically, it is set by professionals and will not be elaborated here.

[0025] The dynamic adjustment coefficient reflects the local state change trend of the key monitoring area during operation. The larger the dynamic adjustment coefficient, the lower the operating stability of the key monitoring area; Associate the stability index with the position of the component where the key monitoring area is located to obtain the stability index weights of different key monitoring areas, and calculate the direction of structural symmetry imbalance: , where is the centroid coordinate of the left part of the section, is the centroid coordinate of the right part of the section, is the offset vector; Calculate the cosine value of the angle between the centroid coordinate of the key monitoring area and the offset vector: , where is the center coordinate of the i-th key monitoring area, is the cosine value of the angle of the i-th key monitoring area; Use the cosine value of the angle of the key monitoring area as the stability index weight of the key monitoring area, and combine the stability index and the dynamic adjustment coefficient to determine the monitoring range of each key monitoring area; Normalize the stability index and dynamic adjustment coefficient of the key monitoring area, and calculate the monitoring range through non-linear function combination: , where and are preset adjustment factors, is the monitoring range of the i-th key monitoring area; It should be noted that reflects the degree of offset of the symmetry of the key monitoring area. The larger the angle, the the larger the value, indicating that the key monitoring area is more deviated from the axis, the structure of the key monitoring area is fragile, and the monitoring range is expanded. The preset adjustment factor allocates different monitoring boundaries according to the operating state differences of different key monitoring areas, which is specifically set by professionals.

[0026] Transmit the monitoring range of the key monitoring area to the quality assessment module for subsequent assessment of the operation quality of the screw pump.

[0027] In the quality assessment module, receive the monitoring range transmitted from the equipment identification module , the monitoring range is calculated by the device identification module based on the comprehensive stability index, dynamic adjustment coefficient, and offset amplitude, representing the physical expansion degree of the current monitoring object, and is used to quantify the monitoring coverage boundary of each key monitoring area under the current operating conditions; The quality assessment module presets two monitoring thresholds, denoted as the first monitoring threshold and the second monitoring threshold , where, satisfying < , the first monitoring threshold and the second monitoring threshold are determined by professionals through experiments based on the structural parameters of the screw pump, historical operation data, and environmental adaptability requirements, and are stored in the quality assessment module in the form of a static configuration table, which will not be elaborated here; Based on the first monitoring threshold and the second monitoring threshold, the quality assessment module performs the following classification and judgment logic on the current operation quality type of the screw pump: If , then it is determined that the operation quality type of the screw pump is excellent; If , then it is determined that the operation quality type of the screw pump is medium; If , then it is determined that the operation quality type of the screw pump is poor; The operation quality type reflects the relationship between the monitoring coverage degree of the key monitoring area and the potential thermal risk. That is, when the working temperature rises, the larger the monitoring range, the more serious the heat dissipation space is limited, the more obvious the heat concentration effect is, resulting in an increase in the risk of structural heat fatigue. Therefore, it is determined that the operation quality is poor; The quality assessment module generates structured operation quality type data based on the above determination results. The operation quality type and the monitoring range are transmitted to the monitoring optimization module together for the adjustment of the monitoring strategy in the next stage. At the same time, the quality assessment module sends the operation quality type to the data acquisition module to enable it to perform the subsequent associated data acquisition tasks; Through the above process, the quality assessment module realizes the hierarchical evaluation of the operation quality type, effectively establishes the association between the change of the monitoring range and the operation stability, and classifies the monitoring status through two bounded thresholds, providing a clear operation status input for the subsequent modules, and ensuring that the entire monitoring system has good adaptability and response ability.

[0028] Upon receiving the operation quality type transmitted by the quality assessment module, regardless of whether the operation quality type is excellent, medium, or poor, the data acquisition module executes a fixed acquisition process. The data acquisition module acquires the working temperature of the current screw pump, and the working temperature is acquired by a temperature sensor disposed on the main body of the screw pump. Synchronously acquire the key position spacing of the current key monitoring area, where the key position spacing represents the minimum Euclidean distance between the center point of the current key monitoring area and the center points of its adjacent multiple key monitoring areas. The specific calculation formula for the key position spacing is: ; where is the key position spacing, is the center coordinate of the current key monitoring area i, and N(i) represents the set of multiple key monitoring areas adjacent to the key area i; After the acquisition is completed, the data acquisition module transmits the working temperature, the key position spacing, and the operation quality type to the monitoring and optimization module. After receiving the above parameters, the monitoring and optimization module first selects the corresponding monitoring range adjustment mode according to the operation quality type; If the operation quality type is excellent, select the monitoring range adjustment mode as the holding mode to maintain the current monitoring range; If the operation quality type is medium, select the monitoring range adjustment mode as the contraction mode to contract the monitoring range; If the operation quality type is poor, select the monitoring range adjustment mode as the key optimization mode for re-evaluation; In the holding mode, the monitoring and optimization module maintains the monitoring range and does not perform further adjustment operations; In the contraction mode, construct the monitoring range, the working temperature, and the key position spacing into a contraction feature vector, and input the contraction feature vector as an input into the contraction mode support vector regression model that has been trained with historical operation data. The contraction mode support vector regression model uses a radial basis kernel function to achieve non-linear mapping, and its output is the proportional coefficient by which the monitoring range needs to be reduced; Based on the proportional coefficient by which the monitoring range needs to be reduced, calculate the monitoring range adjusted in the contraction mode, and use the product of the difference between 1 and the proportional coefficient by which the monitoring range needs to be reduced and the monitoring range as the monitoring range adjusted in the contraction mode; The proportional coefficient by which the monitoring range in the contraction mode needs to be reduced is directly output by the support vector regression model. The adjustment amplitude is kept mild, and it only responds to the regression trend of the historical sample model under medium performance, and there is no additional risk amplification factor control, which is suitable for lightweight intervention when the operation quality type is medium.

[0029] In the key optimization mode, the monitoring and optimization module also receives and constructs an optimization feature vector, where the meanings of the parameters are the same as those above. The optimization feature vector is input into the optimization mode support vector regression model, which is trained based on a non-linear kernel function and historical key fault area samples and outputs a target shrinkage ratio. The value range of the target shrinkage ratio is higher than the ratio coefficient by which the currently monitored range needs to be reduced in the shrinkage mode, reflecting the high-risk degree of the operating state. On the basis of obtaining the target shrinkage ratio, the monitoring and optimization module further introduces a joint risk correction value of the working temperature and the distance between key positions. The calculation formula is as follows: ; where is the empirical risk adjustment factor, is the working temperature, is the maximum working temperature, is a small positive constant; The calculation method of the monitored range after adjustment in the key optimization mode is to multiply the difference between 1 and the product of the target shrinkage ratio and the joint risk correction value by the monitored range; The target shrinkage ratio output by the support vector regression model in the key optimization mode is usually large, and a multiplicative amplification factor of the working temperature and the distance between key positions is introduced to dynamically strengthen the monitoring shrinkage. It is applicable to the active intervention scenario with poor operation quality type and has stronger responsiveness and protection ability.

[0030] It should be noted that the temperature sensor is a sensing device used to real-time sense and collect the temperature parameters of the environment or the surface of components during the operation of the device. The Euclidean distance is used to calculate the straight-line distance between two points in a multi-dimensional space and is the basic measurement method for evaluating the distance between key positions. The support vector regression model is a machine learning model based on statistical learning theory and belongs to the regression extension form of the support vector machine algorithm. The support vector regression model realizes the non-linear mapping between the input features and the target output by constructing an optimal regression hyperplane in a high-dimensional feature space.

[0031] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to get a formula closest to the real situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0032] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center in a wired or wireless (such as infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that contains a set of one or more available media. The available media can be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0033] It should be understood that in various embodiments of the present application, the magnitudes of the serial numbers of the above processes do not mean the order of execution, and the order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0034] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0035] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be repeated herein.

[0036] In several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of devices or units can be in electrical, mechanical, or other forms.

[0037] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0038] In addition, in each embodiment of this application, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0039] If the above functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art or part of this technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of this application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0040] As described above, the above are only the specific implementation manners of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed in this application can easily think of changes or substitutions, which should all be covered by the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

Claims

1. A remote control system for a screw pump with multi-parameter adjustment and fault pre-diagnosis, characterized in that: It includes a data acquisition module, a device identification module, a quality assessment module, and a monitoring and optimization module; The data acquisition module is used to extract the key characteristic values of the operation state of the screw pump, obtain the symmetry information of the screw pump, transmit the key characteristic values and symmetry information to the device identification module, after receiving the screw pump label passed in by the device identification module, obtain the axial center offset and surface wear degree of the screw pump and transmit them back to the device identification module, after receiving the screw pump operation quality type passed in by the quality assessment module, collect the working temperature and key position spacing of the screw pump and send them to the monitoring and optimization module; The device identification module determines multiple key monitoring areas in the operation state of the screw pump according to the key characteristic values, calculates the stability index of the screw pump according to the symmetry information, and sets the screw pump label to be transmitted to the data acquisition module; after receiving the axial center offset of the screw pump, calculate the offset amplitude for comprehensive analysis and calculate the dynamic adjustment coefficient, and determine the monitoring range of each key monitoring area in combination with the stability index and dynamic adjustment coefficient of the screw pump; The quality assessment module is used to receive the monitoring range, compare each key monitoring area, evaluate the operation quality type of the screw pump, and transmit the monitoring range to the monitoring and optimization module; Send the screw pump operation quality type to the data acquisition module and the monitoring and optimization module; The monitoring and optimization module selects a monitoring range adjustment mode according to the screw pump operation quality type, and re-evaluates the monitoring range by using the support vector machine regression algorithm in combination with the working temperature and key position spacing.

2. The remote control system for a screw pump with multi-parameter adjustment and fault pre-diagnosis according to claim 1, characterized in that: Preset an acquisition period and evenly divide it into multiple acquisition moments, and obtain the acceleration values and pressure values of different components of the screw pump; Comprehensively calculate the vibration amplitude of the acceleration values of the same component at each acquisition moment; Take the absolute value of the difference between the pressure values at the inlet end and the outlet end of different components in the screw pump sealing structure to obtain the pressure deviation; Obtain the three-dimensional model of the screw pump, construct a vertical section based on the main axis of the three-dimensional model, divide the three-dimensional model into two symmetric parts, and obtain the structural volumes on both sides of the vertical section as symmetry information.

3. The remote control system for a screw pump with multi-parameter adjustment and fault pre-diagnosis according to claim 1, characterized in that: After receiving the screw pump label, obtain the axial center coordinates during the operation of the screw pump, and evenly divide the main axis into multiple vertical cross-sections along the main axis direction; Calculate the distance between the centroid coordinates of each cross-section and the centroid coordinates of the corresponding cross-section in the non-operating state as the axial center offset of the screw pump; Obtain the height at different coordinates through the three-dimensional model of the screw pump, and take the difference from the height at the corresponding coordinates in the non-operating state to obtain the wear depth; Calculate the surface wear degree of each component through area integration of each wear depth; Obtain the boundary coordinates of the key monitoring area, calculate the Euclidean distance from adjacent multiple key monitoring areas, and take the minimum value of the Euclidean distance as the key position spacing; Collect the working temperatures of different areas during the operation of the screw pump, and take the average value as the working temperature of the screw pump.

4. A remote control system for screw pumps with multi-parameter adjustment and fault pre-diagnosis according to claim 2, characterized in that: A preset amplitude threshold and a deviation threshold are respectively compared with the vibration amplitude and the pressure deviation to determine the key monitoring area: If the vibration amplitude is greater than the amplitude threshold or the pressure deviation is greater than the deviation threshold, the corresponding part is judged as the key monitoring area; If the vibration amplitude is less than or equal to the amplitude threshold and the pressure deviation is less than or equal to the deviation threshold, the corresponding part is judged as a non-key monitoring area; A stability index is calculated based on symmetry information; If there is a key monitoring area in the screw pump, the components in the key monitoring area are numbered and marked.

5. A remote control system for screw pumps with multi-parameter adjustment and fault pre-diagnosis according to claim 4, characterized in that: The offset amplitude is calculated from the axial offset of the screw pump; After the surface wear degree and the offset amplitude are respectively normalized, a dynamic adjustment coefficient is calculated through an exponential regression algorithm; The stability index is associated with the position of the component in the key monitoring area for calculation to obtain the stability index of different key monitoring areas; The stability index and the dynamic adjustment coefficient of the key monitoring area are normalized, and the monitoring range is calculated through a non-linear function.

6. A remote control system for screw pumps with multi-parameter adjustment and fault pre-diagnosis according to claim 5, characterized in that: A first monitoring threshold and a second monitoring threshold are preset, and the first monitoring threshold is less than the second monitoring threshold; If the monitoring range is less than or equal to the first monitoring threshold, it is determined that the operation quality type of the screw pump is excellent; If the monitoring range is greater than the first monitoring threshold and less than or equal to the second monitoring threshold, it is determined that the operation quality type of the screw pump is medium; If the monitoring range is greater than the second monitoring threshold, it is determined that the operation quality type of the screw pump is poor.

7. A remote control system for screw pumps with multi-parameter adjustment and fault pre-diagnosis according to claim 6, characterized in that: The working temperature is collected; The minimum Euclidean distance between the center point of the current key monitoring area and the center points of multiple adjacent key monitoring areas is calculated to obtain the key position spacing; The monitoring range adjustment mode is selected according to the operation quality type; If the operation quality type is excellent, the monitoring range adjustment mode is selected as the hold mode; If the operation quality type is medium, the monitoring range adjustment mode is selected as the shrinkage mode; If the operation quality type is poor, the monitoring range adjustment mode is selected as the key optimization mode.

8. A remote control system for screw pumps with multi-parameter adjustment and fault pre-diagnosis according to claim 7, characterized in that: In the hold mode, no adjustment operation is performed; In the shrinkage mode, the monitoring range, the working temperature, and the key position spacing are constructed into a shrinkage feature vector; The shrinkage feature vector is used as an input and fed into a shrinkage mode support vector regression model that has been trained with historical operation data; The shrinkage mode support vector regression model uses a radial basis kernel function to achieve non-linear mapping and outputs the proportional coefficient by which the monitoring range needs to be reduced; The difference between one and the proportional coefficient by which the monitoring range needs to be reduced is calculated and multiplied by the monitoring range to obtain the monitoring range after adjustment in the shrinkage mode.

9. A remote control system for a screw pump with multi-parameter adjustment and fault pre-diagnosis according to claim 7, characterized in that: In the key optimization mode, the monitoring range, working temperature, and the distance between key positions are constructed as an optimization feature vector; The optimization feature vector is input into the optimization mode support vector regression model; The optimization mode support vector regression model is trained based on a non-linear kernel function and historical key fault area samples, and outputs a target shrinkage ratio; Introduce the combined risk correction value of the working temperature and the spacing of key positions, and the calculation formula is ; Among them, is the empirical risk adjustment factor, is the working temperature, is the maximum working temperature, and ε is a small positive constant; Calculate the difference between the monitoring range multiplied by one and the product of the target shrinkage ratio and the joint risk correction value to obtain the adjusted monitoring range in the key optimization mode.

Images