Screw pump working condition monitoring method and device, electronic equipment and storage medium
By using a screw pump condition monitoring method based on convolutional neural networks, the operating status of screw pumps can be identified in real time, solving the problems of low monitoring efficiency and low accuracy in existing technologies, and realizing efficient fault diagnosis and equipment management.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-21
- Publication Date
- 2026-03-03
AI Technical Summary
Existing technologies for monitoring the operating conditions of screw pumps are inefficient and inaccurate, resulting in inadequate management of screw pump wells.
A screw pump operating condition monitoring method based on a wide convolutional kernel deep convolutional neural network is adopted. By acquiring operating condition curves and using a convolutional neural network model to identify effective features, real-time monitoring and fault diagnosis of screw pump operating conditions are achieved.
It has improved the management level of screw pump wells, reduced downtime due to malfunctions, extended equipment life, optimized the production process, and increased production efficiency.
Smart Images
Figure CN121600530A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of oilfield extraction equipment technology, and in particular to a screw pump operating condition monitoring method, device, electronic equipment and storage medium. Background Technology
[0002] As a highly adaptable oil production equipment, screw pumps are increasingly used in oil wells due to continuous improvements in manufacturing and application technologies. How to further improve the technical and management levels of screw pumps in the oil production process has become a common concern for oilfield engineers.
[0003] Monitoring the operating status of screw pumps and collecting relevant operating parameters to determine the working status of oil wells is crucial for improving the management level of screw pump wells. Currently, the main methods for fault diagnosis of screw pumps are manual inspection and parameter upper and lower limit calibration, which are inefficient and lack accuracy. Summary of the Invention
[0004] This invention provides a method, device, electronic equipment, and storage medium for monitoring the operating conditions of screw pumps, in order to solve the technical problems of low efficiency and low accuracy in monitoring the operating conditions of screw pumps.
[0005] In a first aspect, the present invention provides a screw pump operating condition monitoring method, comprising: acquiring an operating condition curve of the screw pump, the operating condition curve including at least one of a pressure curve, a vibration curve, and a current curve; inputting the operating condition curve into a wide convolutional kernel deep convolutional neural network to identify effective features; inputting the effective features into a trained screw pump operating condition detection model to output the operating condition type of the screw pump, wherein the screw pump operating condition detection model is based on a convolutional neural network model.
[0006] In some embodiments, before inputting the effective features into the pre-trained screw pump condition detection model, the method further includes: obtaining historical training samples of the screw pump, wherein the historical training samples include historical operating condition curves of the screw pump and corresponding historical operating condition types, wherein the historical operating condition curves include at least one of historical pressure curves, historical vibration curves, and historical current curves; inputting the historical operating condition curves into a wide-kernel deep convolutional neural network to identify historical effective features; and training the convolutional neural network model based on the historical effective features and corresponding historical operating condition types to obtain the trained screw pump condition detection model.
[0007] In some embodiments, the operating condition type includes normal operating condition and fault operating condition type; the fault operating condition type includes at least one of the following: pump does not draw oil, pressure gauge pointer fluctuation is greater than a first preset value, flow rate decrease is greater than a second preset value, shaft power increases by a greater than a third preset value within a preset time, and pump vibration amplitude is greater than a fourth preset value.
[0008] In some embodiments, the method further includes: obtaining the historical fault causes corresponding to the screw pump when the historical operating condition type is a fault operating condition type; training the convolutional neural network model based on historical effective features and the corresponding historical operating condition type to obtain the trained screw pump operating condition detection model includes: training the convolutional neural network model based on historical effective features, the corresponding historical operating condition type and the historical fault causes to obtain the trained screw pump operating condition detection model; then inputting the effective features into the trained screw pump operating condition detection model and outputting the operating condition type of the screw pump includes: inputting the effective features into the trained screw pump operating condition detection model and outputting the fault operating condition type and fault cause of the screw pump.
[0009] In some embodiments, the method further includes: correcting the operating condition type output by the screw pump operating condition detection model according to the actual operating condition type of the screw pump to form a new training sample; and retraining the trained screw pump operating condition detection model based on the new training sample.
[0010] Secondly, the present invention provides a screw pump operating condition monitoring device, comprising: an acquisition module for acquiring an operating condition curve of the screw pump, the operating condition curve including at least one of a pressure curve, a vibration curve, and a current curve; an identification module for inputting the operating condition curve into a wide convolutional kernel deep convolutional neural network to identify effective features; and a monitoring module for inputting the effective features into a trained screw pump operating condition detection model to output the operating condition type of the screw pump, the screw pump operating condition detection model being based on a convolutional neural network model.
[0011] In some embodiments, the apparatus further includes a training module; the acquisition module is further configured to acquire historical training samples of the screw pump, the historical training samples including historical operating condition curves of the screw pump and corresponding historical operating condition types, the historical operating condition curves including at least one of historical pressure curves, historical vibration curves, and historical current curves; the identification module is further configured to input the historical operating condition curves into a wide convolutional kernel deep convolutional neural network to identify historical effective features; the training module is further configured to train the convolutional neural network model based on the historical effective features and the corresponding historical operating condition types to obtain the trained screw pump operating condition detection model.
[0012] In some embodiments, the operating condition type includes normal operating condition and fault operating condition type; the fault operating condition type includes at least one of the following: pump does not draw oil, pressure gauge pointer fluctuation is greater than a first preset value, flow rate decrease is greater than a second preset value, shaft power increases by a greater than a third preset value within a preset time, and pump vibration amplitude is greater than a fourth preset value.
[0013] Thirdly, the present invention provides an electronic device, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; the memory is used to store computer programs; and the processor, when executing the program stored in the memory, implements the steps of the screw pump condition monitoring method described in any one of the first aspects.
[0014] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, characterized in that, when the computer program is executed by a processor, it implements the steps of the screw pump condition monitoring method as described in any of the first aspects.
[0015] The screw pump operating condition monitoring method, device, electronic equipment, and storage medium provided in this invention utilize a convolutional neural network reinforcement learning model for real-time monitoring of screw pump operating conditions. This enables timely fault identification, significantly improving the effectiveness and relevance of screw pump well management measures. By diagnosing and adjusting operating parameters in real time, the potential of the oil well can be fully utilized to increase production. Furthermore, damage to the screw pump caused by improper operating parameters can be reduced, extending its service life. Maintaining the oil well under a reasonable production pressure differential is beneficial for ensuring its long-term stable operation. In summary, this invention not only improves the management level of screw pump wells but also helps optimize the production process, increase production efficiency, and reduce downtime due to malfunctions, thus having a positive impact on oilfield production and operation. Attached Figure Description
[0016] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.
[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0018] Figure 1 This is a flowchart illustrating a screw pump operating condition monitoring method provided in an embodiment of the present invention.
[0019] Figure 2A flowchart illustrating a training method for a screw pump operating condition detection model provided in an embodiment of the present invention;
[0020] Figure 3 This is a schematic diagram of the structure of a screw pump operating condition monitoring device provided in an embodiment of the present invention;
[0021] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation
[0022] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0023] Figure 1 This is a flowchart illustrating a screw pump condition monitoring method provided in an embodiment of the present invention, applicable to a screw pump condition monitoring device, or an electronic device equipped with a screw pump condition monitoring device. Figure 1 As shown, the screw pump operating condition monitoring method includes:
[0024] Step S101: Obtain the operating condition curve of the screw pump, wherein the operating condition curve includes at least one of the pressure curve, vibration curve and current curve.
[0025] Specifically, the operating condition curves generated by the screw pump during operation are obtained, including at least one of the pressure curve, vibration curve, and current curve. These curves reflect the state and performance of the screw pump under different operating conditions. For example, the pressure curve shows the pressure changes of the screw pump under different operating conditions, including inlet and outlet pressures. Pressure is an important parameter for the operation of the screw pump, affecting its ability and efficiency in conveying liquids. Similarly, the vibration curve reflects the vibration of the screw pump during operation. Abnormal vibration may indicate a malfunction or abnormal operating condition of the equipment. Furthermore, the current curve shows the current consumption of the screw pump under different operating conditions. It is an important parameter of the screw pump drive motor and can reflect the pump's load and operating status.
[0026] Furthermore, the operating condition curve is a curve showing the change of operating parameters over a period of time. If there are many missing or outlier values on the operating condition curve, the curve can be considered invalid. In this case, the operating condition curve for the next time period will be collected, and subsequent steps will be performed.
[0027] Step S102: Input the operating condition curve into a wide convolutional kernel deep convolutional neural network to identify effective features.
[0028] Specifically, the current, vibration, and pressure curves are processed through a Deep Convolutional Neural Network (WDCNN) with wide kernels to identify effective features. The first layer of the WDCNN has a large convolutional kernel, followed by 3×1 small convolutional kernels to remove features that are not helpful for diagnosing operating conditions.
[0029] Step S103: Input the effective features into the trained screw pump condition detection model and output the screw pump condition type. The screw pump condition detection model is based on a convolutional neural network model.
[0030] Specifically, the effective features extracted from the operating condition curves are input into a pre-trained screw pump fault detection model. This model, based on a convolutional neural network, is used to analyze features and identify the operating condition types of the screw pump in order to detect potential faults or problems.
[0031] The screw pump operating condition monitoring method provided in this invention extracts effective features from the screw pump's operating condition curve and inputs these features into an operating condition detection model to monitor and detect faults in the screw pump. By diagnosing in real time and adjusting operating parameters promptly, the potential of the oil well can be fully utilized to increase production. Furthermore, damage to the screw pump caused by improper operating parameters can be reduced, extending its service life. Maintaining the oil well operating under a reasonable production pressure differential is beneficial for ensuring its long-term stable operation.
[0032] Based on the above embodiments, Figure 2 This is a flowchart illustrating a training method for a screw pump operating condition detection model provided in an embodiment of the present invention. Figure 2 As shown, the method includes:
[0033] Step S201: Obtain historical training samples of the screw pump. The historical training samples include historical operating condition curves of the screw pump and corresponding historical operating condition types. The historical operating condition curves include at least one of historical pressure curves, historical vibration curves, and historical current curves.
[0034] Step S202: Input the historical operating condition curve into a wide convolutional kernel deep convolutional neural network to identify historical effective features.
[0035] Step S203: Train the convolutional neural network model based on historical effective features and corresponding historical operating condition types to obtain the trained screw pump operating condition detection model.
[0036] Specifically, firstly, historical training samples of the screw pump are obtained. These samples include historical operating condition curves of the screw pump and the corresponding historical operating condition types. The operating condition curves in the historical training samples cover historical pressure curves, historical vibration curves, and historical current curves. Then, the historical operating condition curves are input into a deep convolutional neural network with wide convolutional kernels to identify historical effective features. This step aims to extract useful feature information from the historical operating condition curves through a deep learning network, laying the foundation for subsequent model training. Finally, the convolutional neural network model is trained based on the historical effective features and the corresponding historical operating condition types to obtain a fully trained screw pump operating condition detection model. In this step, the model is trained using historical effective features and the corresponding operating condition types so that it can accurately identify the screw pump status under different operating conditions.
[0037] In some embodiments, the operating condition type includes normal operating condition and fault operating condition type; the fault operating condition type includes at least one of the following: pump does not draw oil, pressure gauge pointer fluctuation is greater than a first preset value, flow rate decrease is greater than a second preset value, shaft power increases by a greater than a third preset value within a preset time, and pump vibration amplitude is greater than a fourth preset value.
[0038] Specifically, the operating conditions of a screw pump include normal operation and failure. Faults can be further classified into types such as pump not sucking oil, large fluctuations in pressure gauge pointer, decreased flow rate, sharp increase in shaft power, and excessive pump vibration.
[0039] In some embodiments, the method further includes: obtaining the historical fault causes corresponding to the screw pump when the historical operating condition type is a fault operating condition type; step S203 includes: training a convolutional neural network model based on historical effective features, the corresponding historical operating condition type, and the historical fault causes to obtain the trained screw pump operating condition detection model; then step S103 includes: inputting the effective features into the trained screw pump operating condition detection model, and outputting the fault operating condition type and fault cause of the screw pump.
[0040] Specifically, for each type of failure, possible causes are collected, and these causes are used to train the model. This ensures that the final trained model can not only identify the failure type but also determine the cause, enabling staff to take timely and appropriate measures to address the actual production oil wells. The possible causes for each failure type are shown in Table 1.
[0041] Table 1
[0042]
[0043]
[0044] In some embodiments, the method further includes: correcting the operating condition type output by the screw pump operating condition detection model according to the actual operating condition type of the screw pump to form a new training sample; and retraining the trained screw pump operating condition detection model based on the new training sample.
[0045] Specifically, staff members combine the detection results output by the model with the actual production situation to verify the accuracy of the results and correct any erroneous results. Then, the correct results and the corrected results are used to construct a new training sample, which is then used to retrain the screw pump operating condition detection model.
[0046] It should be noted that by using new training samples to perform reinforcement learning on the model, the model's adaptability can be effectively improved. Through repeated operational condition diagnosis and continuous reinforcement learning, the system can improve the accuracy of operational condition diagnosis, while also addressing errors that may arise due to insufficient sample data and differences in actual production data. This process achieves the effect of gradually improving the accuracy of the neural network during use.
[0047] Based on the aforementioned embodiments, historical training samples of screw pumps are obtained. These historical training samples include historical operating condition curves of the screw pumps and corresponding historical operating condition types. The historical operating condition curves include at least one of historical pressure curves, historical vibration curves, and historical current curves. These historical operating condition curves are input into a deep convolutional neural network with a wide kernel to identify effective historical features. The convolutional neural network model is then trained based on these effective historical features and the corresponding historical operating condition types to obtain the trained screw pump operating condition detection model. This allows for the establishment of a deep learning-based screw pump operating condition detection model, which can utilize information from historical data to perform real-time monitoring and diagnosis of the screw pump's operating condition. This method can help improve the management level of screw pumps, reduce failures, optimize the production process, increase production efficiency, and extend equipment life, thereby having a positive impact on oilfield production and operation.
[0048] Figure 3 This is a schematic diagram of a screw pump operating condition monitoring device provided in an embodiment of the present invention, as shown below. Figure 3 As shown, the screw pump condition monitoring device includes:
[0049] The acquisition module 301 is used to acquire the operating condition curve of the screw pump, which includes at least one of pressure curve, vibration curve and current curve; the identification module 302 is used to input the operating condition curve into a wide convolutional kernel deep convolutional neural network to identify effective features; the monitoring module is used to input the effective features into a trained screw pump operating condition detection model and output the operating condition type of the screw pump, wherein the screw pump operating condition detection model is based on a convolutional neural network model.
[0050] In some embodiments, the device further includes a training module 304; the acquisition module 301 is further configured to acquire historical training samples of the screw pump, the historical training samples including historical operating condition curves of the screw pump and corresponding historical operating condition types, the historical operating condition curves including at least one of historical pressure curves, historical vibration curves and historical current curves; the identification module 302 is further configured to input the historical operating condition curves into a wide convolutional kernel deep convolutional neural network to identify historical effective features; the training module 304 is configured to train the convolutional neural network model based on the historical effective features and the corresponding historical operating condition types to obtain the trained screw pump operating condition detection model.
[0051] In some embodiments, the operating condition type includes normal operating condition and fault operating condition type; the fault operating condition type includes at least one of the following: pump does not draw oil, pressure gauge pointer fluctuation is greater than a first preset value, flow rate decrease is greater than a second preset value, shaft power increases by a greater than a third preset value within a preset time, and pump vibration amplitude is greater than a fourth preset value.
[0052] In some embodiments, the acquisition module 301 is further configured to: acquire the historical fault causes corresponding to the screw pump when the historical operating condition type is a fault operating condition type; the training module 304 is specifically configured to: train the convolutional neural network model based on the historical effective features, the corresponding historical operating condition type, and the historical fault causes to obtain the trained screw pump operating condition detection model; then the detection module 303 is specifically configured to: input the effective features into the trained screw pump operating condition detection model and output the fault operating condition type and fault cause of the screw pump.
[0053] In some embodiments, the training module 304 is further configured to: correct the operating condition type output by the screw pump operating condition detection model according to the actual operating condition type of the screw pump, thereby forming a new training sample; and retrain the trained screw pump operating condition detection model based on the new training sample.
[0054] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process and corresponding beneficial effects of the screw pump condition monitoring device described above can be referred to the corresponding process in the aforementioned method example, and will not be repeated here.
[0055] like Figure 4 As shown, this embodiment of the invention provides an electronic device, including a processor 401, a communication interface 402, a memory 403, and a communication bus 404, wherein the processor 401, the communication interface 402, and the memory 403 communicate with each other via the communication bus 404.
[0056] Memory 403 is used to store computer programs;
[0057] In one embodiment of the present invention, when the processor 401 executes the program stored in the memory 403, it implements the steps of the screw pump condition monitoring method provided in any of the foregoing method embodiments.
[0058] The electronic device provided in this embodiment of the invention has a similar implementation principle and technical effect to the above embodiments, and will not be described again here.
[0059] The aforementioned memory 403 may be an electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read-Only Memory), EPROM, hard disk, or ROM. Memory 403 has storage space for program code used to perform any of the method steps described above. For example, the storage space for program code may include individual program codes for implementing the various steps in the methods described above. This program code can be read from or written to one or more computer program products. These computer program products include program code carriers such as hard disks, optical discs (CDs), memory cards, or floppy disks. Such computer program products are typically portable or fixed storage units. The storage unit may have storage segments or storage spaces arranged similarly to memory 403 in the aforementioned electronic device. The program code may be compressed, for example, in a suitable form. Typically, the storage unit includes programs for performing the method steps according to embodiments of the invention, i.e., code that can be read by a processor such as 401, which, when run by the electronic device, causes the electronic device to perform the various steps in the methods described above.
[0060] Embodiments of the present invention also provide a computer-readable storage medium. The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the screw pump condition monitoring method described above.
[0061] The computer-readable storage medium may be included in the device / apparatus described in the above embodiments; or it may exist independently and not assembled into the device / apparatus. The computer-readable storage medium carries one or more programs that, when executed, implement the method according to the embodiments of the present invention.
[0062] According to embodiments of the present invention, the computer-readable storage medium may be a non-volatile computer-readable storage medium, such as including, but not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In the present invention, the computer-readable storage medium may 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.
[0063] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.
[0064] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.
Claims
1. A method for monitoring the operating conditions of a screw pump, characterized in that, include: Obtain the operating condition curve of the screw pump, wherein the operating condition curve includes at least one of the pressure curve, vibration curve and current curve; The operating condition curve is input into a deep convolutional neural network with wide kernels to identify effective features; The effective features are input into the trained screw pump condition detection model, which outputs the screw pump condition type. The screw pump condition detection model is based on a convolutional neural network model.
2. The method according to claim 1, characterized in that, Before inputting the effective features into the pre-trained screw pump condition detection model, the process also includes: Obtain historical training samples of the screw pump, the historical training samples include historical operating condition curves of the screw pump and corresponding historical operating condition types, the historical operating condition curves include at least one of historical pressure curves, historical vibration curves and historical current curves; The historical operating condition curves are input into a deep convolutional neural network with wide kernels to identify effective historical features; The convolutional neural network model is trained based on historical effective features and corresponding historical operating condition types to obtain the trained screw pump operating condition detection model.
3. The method according to claim 2, characterized in that, The operating condition types include normal operating conditions and fault operating conditions; The fault conditions include at least one of the following: the pump does not draw oil, the pressure gauge pointer fluctuation is greater than the first preset value, the flow rate decrease is greater than the second preset value, the shaft power increases by a greater than the third preset value within a preset time, and the pump vibration amplitude is greater than the fourth preset value.
4. The method according to claim 3, characterized in that, The method further includes: Obtain the historical fault causes of the screw pump when the historical operating condition type is a fault operating condition type; The process of training a convolutional neural network model based on historical valid features and corresponding historical operating condition types to obtain the trained screw pump operating condition detection model includes: The convolutional neural network model is trained based on historical effective features, corresponding historical operating condition types, and historical fault causes to obtain the trained screw pump operating condition detection model. The step of inputting the effective features into the trained screw pump operating condition detection model and outputting the screw pump operating condition type includes: The effective features are input into the trained screw pump condition detection model, which outputs the fault condition type and fault cause of the screw pump.
5. The method according to any one of claims 2-4, characterized in that, The method further includes: The operating condition type output by the screw pump operating condition detection model is modified according to the actual operating condition type of the screw pump to form a new training sample; The screw pump operating condition detection model is retrained based on the new training samples.
6. A screw pump operating condition monitoring device, characterized in that, include: The acquisition module is used to acquire the operating condition curve of the screw pump, which includes at least one of the pressure curve, vibration curve and current curve. The recognition module is used to input the working condition curve into a wide-kernel deep convolutional neural network to identify effective features; The monitoring module is used to input the effective features into the trained screw pump condition detection model and output the screw pump condition type. The screw pump condition detection model is based on a convolutional neural network model.
7. The apparatus according to claim 6, characterized in that, It also includes a training module; The acquisition module is also used to acquire historical training samples of the screw pump. The historical training samples include historical operating condition curves of the screw pump and corresponding historical operating condition types. The historical operating condition curves include at least one of historical pressure curves, historical vibration curves, and historical current curves. The identification module is also used to input the historical operating condition curve into a wide convolutional kernel deep convolutional neural network to identify historical effective features; The training module is used to train the convolutional neural network model based on historical effective features and corresponding historical operating condition types to obtain the trained screw pump operating condition detection model.
8. The apparatus according to claim 7, characterized in that, The operating condition types include normal operating conditions and fault operating conditions; The fault conditions include at least one of the following: the pump does not draw oil, the pressure gauge pointer fluctuation is greater than the first preset value, the flow rate decrease is greater than the second preset value, the shaft power increases by a greater than the third preset value within a preset time, and the pump vibration amplitude is greater than the fourth preset value.
9. An electronic device, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; When a processor executes a program stored in a memory, it implements the steps of the screw pump condition monitoring method according to any one of claims 1-5.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the screw pump condition monitoring method as described in any one of claims 1-5.