Pump station fault-tolerant control method based on multi-modal data fusion and related equipment

Abstract

The invention provides a pump station fault-tolerant control method and related equipment based on multi-modal data fusion, and the method comprises the steps: obtaining the multi-modal state sensing information of an emulsion pump, and enabling the state sensing information to comprise the steps: obtaining the vibration signals of key parts through a vibration sensor installed at the key part of the emulsion pump; oil temperature, oil pressure and oil level sensing information is obtained through an oil temperature sensor, an oil pressure sensor and an oil level sensor, crankshaft rotating speed and phase sensing information is obtained through a rotating speed sensor, and an emulsion pump operation environment monitoring video stream collected by a camera is used; the multi-mode state sensing information of the emulsion pump is subjected to multiple fusion, and a switching control strategy is output; the fault operation pump is controlled to stop and the standby pump is controlled to start according to the switching control strategy, the early warning requirement for the early fault of the emulsion pump is met, multi-mode state sensing information of the emulsion pump is subjected to multiple fusion, the fault operation pump can be controlled to stop and the standby pump can be controlled to start in time when the fault occurs, and intelligent control over the emulsion pump is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of pump station fault-tolerant control, and in particular to a pump station fault-tolerant control method based on multi-modal data fusion and related equipment. Background Art

[0002] The emulsion pump system is a fluid supply system that provides hydraulic power for the fully-mechanized mining face of a coal mine, and is an important part of the coal mine production system. The emulsion pump system is generally equipped with multiple emulsion pumps, which can be divided into two types: operating pumps and standby pumps. The emulsion pump is equipped with oil temperature, oil pressure and oil level sensors for fault alarm when it leaves the factory. When the sensor alarms, the operation and maintenance personnel next to the emulsion pump system will check the operation of the emulsion pump in time. Relying on experience to eliminate the cause of the fault, other standby pumps are started at the same time to continue to supply the required emulsion to the working face to ensure efficient production of the coal mine. However, since the oil temperature, oil pressure and oil level sensors are slow-changing sensors, it is impossible to capture the emulsion pump failure in time, let alone accurately track the changing trend of the failure. When the emulsion pump fails and the fault worsens seriously, the sensor will have a more obvious change, which cannot meet the early warning needs of the emulsion pump failure. Moreover, since fault diagnosis and equipment control are not linked, the fault diagnosis results are more often just displayed, and the on-duty operation and maintenance personnel are required to manually control the start and stop of the running pump and the standby pump, resulting in the failure to be stopped in time, which can easily cause great losses. Summary of the invention

[0003] The present invention provides a pump station fault-tolerant control method and related equipment based on multimodal data fusion, which are used to solve the defects that the traditional emulsion pump fault monitoring method cannot meet the early warning requirements of the emulsion pump fault and cannot stop the fault in time when it occurs, which easily causes great losses.

[0004] The present invention provides a pump station fault-tolerant control method based on multi-modal data fusion, comprising: Acquire multimodal state perception information of the emulsion pump, the state perception information includes obtaining vibration signals of key components through vibration sensors installed at key parts of the emulsion pump, obtaining oil temperature, oil pressure and oil level perception information through oil temperature, oil pressure and oil level sensors, obtaining crankshaft speed and phase perception information through speed sensors, and using a video stream of monitoring the emulsion pump operating environment collected by a camera; Perform multiple fusions on the multi-modal state perception information of the emulsion pump and output a switching control strategy; The faulty pump is stopped and the standby pump is started according to the switching control strategy.

[0005] According to the pump station fault-tolerant control method based on multimodal data fusion provided by the present invention, the multi-modal state sensing information of the emulsion pump is multiple-fused, including: The key component vibration signal and the crankshaft phase signal are data-level integrated, specifically including: Using the crankshaft phase signal to segment the vibration signal of the key component to obtain a vibration signal sample of a whole cycle; The characteristics of the integral period vibration signal are extracted to obtain the characteristic distribution of the integral period vibration signal samples.

[0006] According to the pump station fault-tolerant control method based on multimodal data fusion provided by the present invention, the multi-modal state sensing information of the emulsion pump is multiple-fused and further comprises: The characteristic distribution of the full-cycle vibration signal sample is fused with the oil temperature, oil pressure and oil level sensing information at the feature level, and the fusion result is input into the health management model based on the neural network to obtain the health status recognition result of the emulsion pump.

[0007] According to the pump station fault-tolerant control method based on multimodal data fusion provided by the present invention, the multimodal state sensing information of the emulsion pump is multiple-fused, and further includes: Based on the video stream of the emulsion pump operating environment collected by the camera, identify whether there is leakage and whether there are people around the equipment; The health status identification result of the emulsion pump is integrated with the presence of leakage faults and whether there are people around the equipment at the decision level, and a switching control strategy is output.

[0008] According to the pump station fault-tolerant control method based on multimodal data fusion provided by the present invention, the switching control strategy includes: When the system issues an alarm, it determines whether the running pump needs to be shut down based on the fault location and fault severity of the alarm; If so, a control command is issued through the control system to shut down the running pump that has failed.

[0009] According to the pump station fault-tolerant control method based on multimodal data fusion provided by the present invention, the switching control strategy also includes: If there are people around the running pump, the emulsion pump station control system will send a signal to remind the maintenance personnel to manually shut down the running pump with the fault and start the standby pump; If there is no one around the running pump, check whether there is anyone around the standby pump. If there is, send a signal to remind the maintenance personnel to manually shut down the faulty running pump and start the standby pump. If there is no one around the operating pump and the standby pump, a control command is issued through the control system to shut down the faulty operating pump and start the standby pump.

[0010] According to the pump station fault-tolerant control method based on multi-modal data fusion provided by the present invention, the starting of the standby pump includes: The accumulated running time of each standby pump is obtained, and the standby pump with the shortest accumulated running time is selected to start.

[0011] The present invention also provides a pump station fault-tolerant control device based on multi-modal data fusion, comprising: An acquisition module is used to acquire multimodal state perception information of the emulsion pump, wherein the state perception information includes acquiring vibration signals of key components through vibration sensors installed at key parts of the emulsion pump, acquiring oil temperature, oil pressure and oil level perception information through oil temperature, oil pressure and oil level sensors, acquiring crankshaft speed and phase perception information through speed sensors, and an emulsion pump operating environment monitoring video stream collected by a camera; A fusion module, used for performing multiple fusions on the multi-modal state perception information of the emulsion pump and outputting a switching control strategy; The control module is used to control the stopping of the faulty operating pump and the starting of the standby pump according to the switching control strategy.

[0012] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the pump station fault-tolerant control method based on multimodal data fusion as described in any one of the above items is implemented.

[0013] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the pump station fault-tolerant control method based on multimodal data fusion as described in any one of the above items is implemented.

[0014] The pump station fault-tolerant control method and related equipment based on multimodal data fusion provided by the present invention obtain multimodal state perception information of the emulsion pump, wherein the state perception information includes obtaining vibration signals of key components through vibration sensors installed at key parts of the emulsion pump, obtaining oil temperature, oil pressure and oil level perception information through oil temperature, oil pressure and oil level sensors, obtaining crankshaft speed and phase perception information through a speed sensor, and using an emulsion pump operating environment monitoring video stream collected by a camera; the multimodal state perception information of the emulsion pump is multi-fused and a switching control strategy is output; the faulty running pump is stopped and the standby pump is started according to the switching control strategy, and the operation of the emulsion pump system is monitored in real time through a variety of sensing devices to meet the early warning requirements of the emulsion pump. The multimodal state perception information of the emulsion pump is multi-fused, and the faulty running pump can be stopped and the standby pump can be started in time when a fault occurs, thereby realizing intelligent control of the emulsion pump. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 It is a flow chart of a pump station fault-tolerant control method based on multi-modal data fusion provided by an embodiment of the present invention; Figure 2 is a schematic diagram of the emulsion pump status monitoring layout provided by an embodiment of the present invention; Figure 3 is a schematic diagram of a flow chart of multimodal data fusion and processing provided by an embodiment of the present invention; Figure 4 is a flow chart of a switching control strategy provided by an embodiment of the present invention; Figure 5 It is a functional structure diagram of a pump station fault-tolerant control device based on multi-modal data fusion provided by an embodiment of the present invention; Figure 6 It is a functional structure diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] Figure 1 A flow chart of a pump station fault-tolerant control method based on multimodal data fusion provided by an embodiment of the present invention is shown in FIG. Figure 1 As shown, the pump station fault-tolerant control method based on multimodal data fusion provided by the embodiment of the present invention includes: Step 101, obtaining multimodal state perception information of the emulsion pump, wherein the state perception information includes obtaining vibration signals of key components through vibration sensors installed at key parts of the emulsion pump, obtaining oil temperature, oil pressure and oil level perception information through oil temperature, oil pressure and oil level sensors, obtaining crankshaft speed and phase perception information through speed sensors, and using a video stream of monitoring the emulsion pump operation environment collected by a camera; In the embodiment of the present invention, vibration sensors are installed at key locations of the emulsion pump on the basis of conventional oil temperature, oil pressure and oil level monitoring to sense the health status of key components in real time, and speed sensors are installed at the crankcase to monitor the crankshaft speed and phase in real time. A multi-channel synchronous vibration monitor host is used to collect status data in real time and at high frequency, so as to achieve a comprehensive detection of the health status of the emulsion pump. A camera is installed near the emulsion pump equipment train to monitor the overall operating environment of the emulsion pump equipment train, and the monitoring range includes one or more emulsion pump group trains. The camera is used to monitor and identify personnel on the one hand, and to monitor and identify leakage faults on the other hand. The emulsion pump system will be equipped with multiple emulsion pumps, and the multiple emulsion pumps are arranged in series. Taking 4 emulsion pumps as an example, 2 are generally used and 2 are spare. A camera can be installed near emulsion pumps No. 1 and No. 4 to jointly monitor the conditions in the areas near the 4 emulsion pumps. Figure 2 All sensor data and camera video streams will be transmitted to the ground server through the underground industrial ring network for data storage, analysis, and recognition.

[0019] Step 102, multiple fusion of multi-modal state perception information of the emulsion pump is performed, and a switching control strategy is output; Step 103: Control the failed pump to stop and the standby pump to start according to the switching control strategy.

[0020] In the traditional pump station fault-tolerant control method, since the oil temperature, oil pressure and oil level sensors are slow-changing sensors, it is impossible to capture the emulsion pump failure in time, and it is even more impossible to accurately track the changing trend of the failure. When the emulsion pump fails and the failure deteriorates seriously, the sensor will have a more obvious change, which cannot meet the early warning needs of the emulsion pump failure. In addition, since fault diagnosis and equipment control are not linked, the fault diagnosis results are more of a display, and the on-duty operation and maintenance personnel are required to manually control the start and stop of the running pump and the standby pump, resulting in the failure to stop in time, which is easy to cause large losses.

[0021] The pump station fault-tolerant control method based on multimodal data fusion provided in an embodiment of the present invention obtains multimodal state perception information of the emulsion pump, wherein the state perception information includes obtaining vibration signals of key components through vibration sensors installed at key parts of the emulsion pump, obtaining oil temperature, oil pressure and oil level perception information through oil temperature, oil pressure and oil level sensors, obtaining crankshaft speed and phase perception information through a speed sensor, and an emulsion pump operating environment monitoring video stream collected by a camera; the multimodal state perception information of the emulsion pump is multi-fused and a switching control strategy is output; the faulty running pump is stopped and the standby pump is started according to the switching control strategy, and the operation of the emulsion pump system is monitored in real time through a variety of sensing devices to meet the early warning requirements of the emulsion pump. The multimodal state perception information of the emulsion pump is multi-fused, and the faulty running pump can be stopped and the standby pump can be started in time when a fault occurs, thereby realizing intelligent control of the emulsion pump.

[0022] Based on any of the above embodiments, the multi-modal state perception information of the emulsion pump is multi-fused including: The key component vibration signal and the crankshaft phase signal are data-level integrated, specifically including: Step 201: segment the vibration signal of the key component using the crankshaft phase signal to obtain a vibration signal sample of a whole cycle; Step 202: extract the characteristics of the vibration signal of the entire period to obtain the characteristic distribution of the samples of the vibration signal of the entire period.

[0023] Based on any of the above embodiments, the multi-mode state perception information of the emulsion pump is multi-fused further comprising: The characteristic distribution of the full-cycle vibration signal sample is fused with the oil temperature, oil pressure and oil level sensing information at the feature level, and the fusion result is input into the health management model based on the neural network to obtain the health status recognition result of the emulsion pump.

[0024] Based on any of the above embodiments, the multi-modal state perception information of the emulsion pump is multi-fused, further comprising: Based on the video stream of the emulsion pump operating environment collected by the camera, identify whether there is leakage and whether there are people around the equipment; The health status identification result of the emulsion pump is integrated with the presence of leakage faults and whether there are people around the equipment at the decision level, and a switching control strategy is output.

[0025] like Figure 3As shown in the figure, the multimodal data of the emulsion pump system is divided into three levels: data, features, and decision-making for fusion. Data-level fusion mainly processes the vibration signals of key components and crankshaft phase signals collected synchronously at high speed. It is necessary to use the crankshaft phase signal to segment the vibration signal to obtain the vibration signal sample of the entire cycle. Taking the vibration signal of the entire cycle as the input signal, the characteristics of the vibration signal are extracted and the feature distribution is constructed. Feature-level fusion mainly integrates the feature distribution of the vibration signal sample of the entire cycle with the oil temperature, oil pressure and oil level data, and uses the neural network-based health management model for data processing and state recognition. Decision-level fusion mainly integrates the equipment health status recognition results based on sensor data and the recognition results based on the camera video stream to generate a switching control strategy.

[0026] Among them, the neural network health management model is trained based on the characteristic distribution of historical vibration signals and historical data of oil temperature, oil pressure and oil level. The emulsion pump health status recognition result output by the neural network health management model includes the emulsion pump failure or the emulsion pump normal status.

[0027] Based on any of the above embodiments, Figure 4 As shown, the switching control strategy includes: When the system issues an alarm, it determines whether the running pump needs to be shut down based on the fault location and fault severity of the alarm; If so, a control command is issued through the control system to shut down the running pump that has failed.

[0028] In an embodiment of the present invention, the switching control strategy further includes: If there are people around the running pump, the emulsion pump station control system will send a signal to remind the maintenance personnel to manually shut down the running pump with a fault and start the standby pump; If there is no one around the running pump, check whether there is anyone around the standby pump. If there is, send a signal to remind the maintenance personnel to manually shut down the faulty running pump and start the standby pump. If there is no one around the operating pump and the standby pump, a control command is issued through the control system to shut down the faulty operating pump and start the standby pump.

[0029] In an embodiment of the present invention, starting the standby pump includes: The accumulated running time of each standby pump is obtained, and the standby pump with the shortest accumulated running time is selected to start.

[0030] In the embodiment of the present invention, the standby pump is started up by accumulating the running time, so as to realize the shutdown of the faulty emulsion pump and the balanced operation of multiple emulsion pumps, reduce the significant losses caused by the deterioration of the fault, and avoid the unbalanced operation of multiple pumps.

[0031] The pump station fault-tolerant control method based on multimodal data fusion provided by the embodiment of the present invention combines conventional temperature, pressure and liquid level monitoring, adds vibration and speed sensors to monitor the status of key components of the emulsion pump, and uses the equipment health management model to perform fault warning and diagnosis; at the same time, a camera is used to monitor the operating environment of the emulsion pump, and an intelligent recognition model is used to determine whether leakage occurs and whether there are people around the equipment. The identification results of whether there are people are fused with the fault diagnosis results, and then a control command is issued to stop the faulty pump and start the standby pump. The fusion and processing method of multimodal data ensures data synchronization, ensures the synchronization of fault diagnosis and personnel identification, realizes the shutdown of the faulty emulsion pump and the balanced operation of multiple emulsion pumps, reduces the significant losses caused by the deterioration of faults, avoids the unbalanced operation of multiple pumps, and damages the life of the pump.

[0032] The pump station fault-tolerant control device based on multimodal data fusion provided by the present invention is described below. The pump station fault-tolerant control device based on multimodal data fusion described below and the pump station fault-tolerant control method based on multimodal data fusion described above can be referenced to each other.

[0033] Figure 5 A schematic diagram of the structure of a pump station fault-tolerant control device based on multimodal data fusion provided by an embodiment of the present invention is shown in FIG. Figure 5 As shown, the pump station fault-tolerant control device based on multimodal data fusion provided by the embodiment of the present invention includes: The acquisition module 501 is used to acquire multimodal state perception information of the emulsion pump, wherein the state perception information includes acquiring vibration signals of key components through vibration sensors installed at key parts of the emulsion pump, acquiring oil temperature, oil pressure and oil level perception information through oil temperature, oil pressure and oil level sensors, acquiring crankshaft speed and phase perception information through speed sensors, and using a video stream of monitoring the emulsion pump operation environment collected by a camera; A fusion module 502 is used to perform multiple fusions on the multi-modal state perception information of the emulsion pump and output a switching control strategy; The control module 503 is used to control the failure-operating pump to stop and the standby pump to start according to the switching control strategy.

[0034] The pump station fault-tolerant control device based on multimodal data fusion provided by the embodiment of the present invention obtains multimodal state perception information of the emulsion pump, wherein the state perception information includes obtaining vibration signals of key components through vibration sensors installed at key parts of the emulsion pump, obtaining oil temperature, oil pressure and oil level perception information through oil temperature, oil pressure and oil level sensors, obtaining crankshaft speed and phase perception information through a speed sensor, and an emulsion pump operation environment monitoring video stream collected by a camera; the multimodal state perception information of the emulsion pump is multi-fused and a switching control strategy is output; the faulty running pump is stopped and the standby pump is started according to the switching control strategy, and the operation of the emulsion pump system is monitored in real time through a variety of sensing devices to meet the early warning requirements of the emulsion pump. The multimodal state perception information of the emulsion pump is multi-fused, and the faulty running pump can be stopped and the standby pump can be started in time when a fault occurs, thereby realizing intelligent control of the emulsion pump.

[0035] Figure 6 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 6 As shown, the electronic device may include: a processor 610, a communication interface 620, a memory 630 and a communication bus 640, wherein the processor 610, the communication interface 620 and the memory 630 communicate with each other through the communication bus 640. The memory 630 includes a computer program, an operating system and acquired data, and the processor 610 may call the logic instructions in the memory 630 to execute a pump station fault-tolerant control method based on multimodal data fusion, the method comprising: acquiring multimodal state perception information of the emulsion pump, the state perception information including acquiring a key component vibration signal through a vibration sensor installed at a key part of the emulsion pump, acquiring oil temperature, oil pressure and oil level perception information through an oil temperature, oil pressure and oil level sensor, acquiring crankshaft speed and phase perception information through a speed sensor, and using a video stream of monitoring the operation environment of the emulsion pump collected by a camera; performing multiple fusions on the multimodal state perception information of the emulsion pump, and outputting a switching control strategy; and controlling the failure operation pump to stop and the standby pump to start according to the switching control strategy.

[0036] In addition, the logic instructions in the above-mentioned memory 630 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention, or the part that contributes to the relevant technology or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0037] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the pump station fault-tolerant control method based on multimodal data fusion provided by the above-mentioned methods, the method comprising: obtaining multimodal state perception information of the emulsion pump, the state perception information comprising obtaining vibration signals of key components through vibration sensors installed at key parts of the emulsion pump, obtaining oil temperature, oil pressure and oil level perception information through oil temperature, oil pressure and oil level sensors, obtaining crankshaft speed and phase perception information through a speed sensor, and using a video stream of the emulsion pump operating environment monitoring collected by a camera; performing multiple fusions on the multimodal state perception information of the emulsion pump, and outputting a switching control strategy; and controlling the stopping of the faulty operating pump and the starting of the standby pump according to the switching control strategy.

[0038] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0039] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiment.

[0040] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A pump station fault-tolerant control method based on multimodal data fusion, characterized in that: include: Acquire multimodal state perception information of the emulsion pump, the state perception information includes obtaining vibration signals of key components through vibration sensors installed at key parts of the emulsion pump, obtaining oil temperature, oil pressure and oil level perception information through oil temperature, oil pressure and oil level sensors, obtaining crankshaft speed and phase perception information through speed sensors, and using a video stream of monitoring the emulsion pump operating environment collected by a camera; Perform multiple fusions on the multi-modal state perception information of the emulsion pump and output a switching control strategy; The faulty pump is stopped and the standby pump is started according to the switching control strategy.

2. The pump station fault-tolerant control method based on multimodal data fusion according to claim 1 is characterized in that: The multi-mode state sensing information of the emulsion pump is multi-fused, including: The key component vibration signal and the crankshaft phase signal are data-level integrated, specifically including: Using the crankshaft phase signal to segment the vibration signal of the key component to obtain a vibration signal sample of a whole cycle; The characteristics of the integral period vibration signal are extracted to obtain the characteristic distribution of the integral period vibration signal samples.

3. The pump station fault-tolerant control method based on multimodal data fusion according to claim 2 is characterized in that: The multi-fusion of the multi-modal state perception information of the emulsion pump further includes: The characteristic distribution of the full-cycle vibration signal sample is fused with the oil temperature, oil pressure and oil level sensing information at the feature level, and the fusion result is input into the health management model based on the neural network to obtain the health status recognition result of the emulsion pump.

4. The pump station fault-tolerant control method based on multimodal data fusion according to claim 3 is characterized in that: The multi-mode state sensing information of the emulsion pump is subjected to multiple fusion, and further comprises: Based on the video stream of the emulsion pump operating environment collected by the camera, identify whether there is leakage and whether there are people around the equipment; The health status identification result of the emulsion pump is integrated with the presence of leakage faults and whether there are people around the equipment at the decision level, and a switching control strategy is output.

5. The pump station fault-tolerant control method based on multimodal data fusion according to claim 4 is characterized in that: The switching control strategy includes: When the system issues an alarm, it determines whether the running pump needs to be shut down based on the fault location and fault severity of the alarm; If so, a control command is issued through the control system to shut down the running pump that has failed.

6. The pump station fault-tolerant control method based on multimodal data fusion according to claim 4 is characterized in that: The switching control strategy also includes: If there is someone around the running pump, the emulsion pump station control system will send a signal to remind the maintenance personnel to manually shut down the running pump with a fault and start the standby pump; If there is no one around the running pump, check whether there is anyone around the standby pump. If there is, send a signal to remind the maintenance personnel to manually shut down the faulty running pump and start the standby pump. If there is no one around the operating pump and the standby pump, a control command is issued through the control system to shut down the faulty operating pump and start the standby pump.

7. The pump station fault-tolerant control method based on multimodal data fusion according to claim 6 is characterized in that: The starting of the standby pump comprises: The accumulated running time of each standby pump is obtained, and the standby pump with the shortest accumulated running time is selected to start.

8. A pump station fault-tolerant control device based on multimodal data fusion, characterized in that: include: An acquisition module is used to acquire multimodal state perception information of the emulsion pump, wherein the state perception information includes acquiring vibration signals of key components through vibration sensors installed at key parts of the emulsion pump, acquiring oil temperature, oil pressure and oil level perception information through oil temperature, oil pressure and oil level sensors, acquiring crankshaft speed and phase perception information through speed sensors, and an emulsion pump operating environment monitoring video stream collected by a camera; A fusion module, used for performing multiple fusions on the multi-modal state perception information of the emulsion pump and outputting a switching control strategy; The control module is used to control the stopping of the faulty operating pump and the starting of the standby pump according to the switching control strategy.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the pump station fault-tolerant control method based on multimodal data fusion as described in any one of claims 1 to 7 is implemented.

10. A non-transitory readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the pump station fault-tolerant control method based on multimodal data fusion as described in any one of claims 1 to 7 is implemented.

Images