A remote control method for an industrial sensor

Abstract

An embodiment of this specification provides a remote control method for industrial sensors. Among them, the method includes: determining at least one sensor and a corresponding target object; obtaining first state information of at least one sensor, where the first state information corresponds to a first time; determining at least one second time based on the first state information, where the second time refers to the time when at least one sensor may have an abnormality; obtaining third state information of at least one target object, where the third state information corresponds to a third time; determining at least one fourth time based on the third state information, where the fourth time refers to the time when at least one target object may have an abnormality; determining a stimulation parameter based on at least one second time and at least one fourth time, where the stimulation parameter includes a target time and a stimulation increase; determining stimulation state information of at least one sensor based on the stimulation parameter; and determining a maintenance command based on the actual state information and the stimulation state information.

Description

Technical Field

[0001] This specification relates to the field of simulation technology, and particularly to a method for remotely controlling an industrial sensor. Background Art

[0002] In the industrial field, a sensor is a device used to monitor, measure, and collect environmental parameters or device status, usually by converting physical or chemical quantities in the environment into electrical signals. Sensors play a crucial role in industrial production and can be used to monitor various parameters such as temperature, humidity, pressure, flow, and current to ensure the stability and safety of the production process. Through sensors, the production status can be monitored and even the status information at future time points can be predicted, enabling problems to be detected in a timely manner and measures to be taken.

[0003] Therefore, it is desirable to propose a method, system, device, and readable storage medium for remotely controlling an industrial sensor, which can improve the accuracy of judging the sensor status and further adjust or intervene in the sensor status through maintenance to cope with expected abnormal situations and ensure the normal operation of the system. Summary of the Invention

[0004] This specification provides a method, system, device, and storage medium for remotely controlling an industrial sensor, which can improve the accuracy of judging the sensor status and further adjust or intervene in the sensor status through maintenance to cope with expected abnormal situations and ensure the normal operation of the system.

[0005] One embodiment of this specification provides a method for remotely controlling an industrial sensor, including: determining at least one sensor and a corresponding target object; acquiring first status information of at least one sensor, where the first status information corresponds to a first time; determining at least one second time based on the first status information, where the second time refers to the time when at least one sensor may have an abnormality; acquiring third status information of at least one target object, where the third status information corresponds to a third time; determining at least one fourth time based on the third status information, where the fourth time refers to the time when at least one target object may have an abnormality; determining a stimulation parameter based on at least one second time and at least one fourth time, where the stimulation parameter includes a target time and a stimulation increase; determining stimulation status information of at least one sensor based on the stimulation parameter; and determining a maintenance command based on the actual status information and the stimulation status information.

[0006] One embodiment of this specification provides a remote control system for industrial sensors, including: a relationship determination module for determining at least one sensor and a corresponding target object; a first acquisition module for acquiring first status information of the at least one sensor, where the first status information corresponds to a first time; a second acquisition module for determining at least one second time based on the first status information, where the second time refers to the time when at least one sensor may have an abnormality; a third acquisition module for acquiring third status information of the at least one target object, where the third status information corresponds to a third time; a fourth acquisition module for determining at least one fourth time based on the third status information, where the fourth time refers to the time when at least one target object may have an abnormality; a stimulation parameter determination module for determining a stimulation parameter based on the at least one second time and the at least one fourth time, where the stimulation parameter includes a target time and a stimulation increase; a stimulation status determination module for determining stimulation status information of at least one sensor based on the stimulation parameter; and a command determination module for determining a maintenance command based on the actual status information and the stimulation status information.

[0007] Some embodiments of this specification also provide a remote control device for industrial sensors, including at least one processor and at least one memory; the at least one memory is used to store computer instructions; the at least one processor is used to implement the remote control method of industrial sensors described in any one of the above embodiments.

[0008] One embodiment of this specification also provides a computer-readable storage medium, which stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the remote control method of industrial sensors described in any one of the above embodiments. Description of the Drawings

[0009] This specification will be further described by way of exemplary embodiments, and these exemplary embodiments will be described in detail through the drawings. These embodiments are not restrictive. In these embodiments, the same numbers represent the same structures, where:

[0010] Figure 1 is a schematic diagram of the application scenario of the remote control system for industrial sensors shown in some embodiments of this specification;

[0011] Figure 2 is an exemplary module diagram of the remote control system for industrial sensors shown in some embodiments of this specification;

[0012] Figure 3 is an exemplary flowchart of the remote control method for industrial sensors shown in some embodiments of this specification. Detailed Description of the Embodiments

[0013] To more clearly illustrate the technical solutions of the embodiments of this specification, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some examples or embodiments of this specification. For those of ordinary skill in the art, without creative efforts, this specification can also be applied to other similar scenarios based on these drawings. Unless obvious from the language context or otherwise stated, the same reference numerals in the figures represent the same structure or operation.

[0014] It should be understood that the "system", "device", "unit" and / or "module" used herein is a way to distinguish different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the said words can be replaced by other expressions.

[0015] As shown in this specification and the claims, unless the context clearly indicates an exceptional situation, words such as "a", "an", "one" and / or "the" are not specifically singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0016] Flowcharts are used in this specification to illustrate the operations performed by the systems according to the embodiments of this specification. It should be understood that the operations before or after may not necessarily be executed precisely in sequence. On the contrary, they can be executed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or several steps can be removed from these processes.

[0017] Figure 1 It is a schematic diagram of the application scenario of the remote control system of industrial sensors shown in some embodiments of this specification.

[0018] In some embodiments, the application scenario 100 of the remote control system of industrial sensors may include a sensor 110, a target object 120, a processor 130, a user terminal 140, a storage device 150, and a network 160.

[0019] The sensor 110 is responsible for monitoring the environment or device status in real time and transmitting the status information of the target object 120 collected to the processor for analysis and processing. In some embodiments, the status data of the sensor includes the response speed and output data volume of the sensor. In some embodiments, the status data of the target object 120 includes working data such as current, voltage, and temperature that can be monitored by the sensor.

[0020] The storage device 150 can be used to store data and / or instructions. Data refers to the digital representation of information and can include various types, such as binary data, text data, image data, video data, etc. Instructions refer to programs that can control a device or component to perform specific functions. In some embodiments, the data can include data related to the sensor 110 and the user 140, etc. In some embodiments, the storage device 150 can store the data and / or instructions that the processor 130 uses to execute or utilize to complete the exemplary methods described in this specification. For example, the storage device 150 can store information related to the sensor 110. As another example, the storage device 150 can store one or more machine learning models.

[0021] In some embodiments, the storage device 150 can be a part of the processor 130. The storage device 150 can include one or more storage components, and each storage component can be an independent device or a part of other devices. In some embodiments, the storage device 150 can include a random access memory (RAM), a read-only memory (ROM), a mass storage device, a removable storage device, a volatile read-write memory, etc., or any combination thereof. Exemplarily, the mass storage device can include a magnetic disk, an optical disk, a solid-state disk, etc. In some embodiments, the storage device 150 can be implemented on a cloud platform. Exemplarily, the cloud platform can include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-layer cloud, etc., or any combination thereof.

[0022] The processor 130 can be used to process data and / or information from at least one component of the application scenario 100 of the remote control system of industrial sensors or an external data source (such as a cloud data center). The processor 130 can access and / or receive data and information via the network 160 or directly connected to the storage device 150. For example, the processor 130 can be directly connected to the storage device 150 and receive information related to the sensor 110.

[0023] In some embodiments, the processor 130 can include one or more sub-processing devices (for example, a single-core processing device or a multi-core multi-chip processing device). Exemplarily, the processor 130 can include a central processing unit (CPU), an application-specific integrated circuit (ASIC), an application-specific instruction processor (ASIP), a graphics processing unit (GPU), a physics processing unit (PPU), a digital signal processor (DSP), a field-programmable gate array (FPGA), a programmable logic device (PLD), a controller, a microcontroller unit, a reduced instruction set computer (RISC), a microprocessor, etc., or any combination of the above.

[0024] The user terminal 140 may refer to one or more terminal devices or software used by a user. In some embodiments, the user terminal 140 may be a mobile device, a tablet computer, a laptop computer, etc., or any combination thereof. In some embodiments, the user terminal 140 may interact with other components in the application scenario 100 of the remote control system of industrial sensors via the network 160.

[0025] It should be noted that the application scenario is provided for illustrative purposes only and is not intended to limit the scope of this specification. For those of ordinary skill in the art, various modifications or changes can be made according to the description of this specification. For example, the application scenario may also include a database. Again, for example, the application scenario may implement similar or different functions on other devices. However, the changes and modifications will not depart from the scope of this specification.

[0026] Figure 2 is an exemplary module diagram of the remote control system of industrial sensors shown according to some embodiments of this specification. As Figure 2 shown, the remote control system 200 of industrial sensors may include a relationship determination module 210, a first acquisition module 220, a second acquisition module 230, a third acquisition module 240, a fourth acquisition module 250, a stimulation parameter determination module 260, a stimulation state determination module 270, and a command determination module 280.

[0027] The relationship determination module 210 is configured to determine at least one sensor and the corresponding target object.

[0028] The first acquisition module 220 is configured to acquire the first state information of at least one sensor, and the first state information corresponds to the first time.

[0029] The second acquisition module 230 is configured to determine at least one second time based on the first state information, and the second time refers to the time when at least one sensor may have an abnormality.

[0030] In some embodiments, the second acquisition module 230 includes: a vector determination module, configured to determine a first state information vector based on the first state information; a historical first state determination module, configured to determine at least one historical first state information vector through a sensor state information vector database based on the first state information vector; a historical first time determination module, configured to determine at least one historical first time based on at least one historical first state information vector; a historical second state determination module, configured to determine at least one historical second state information based on at least one historical first time and the historical first state information vector; a historical second time determination module, configured to determine at least one historical second time based on at least one historical second state information; a time difference determination module, configured to determine at least one sensor historical time difference based on at least one pair of corresponding historical first times and historical second times; and a second time acquisition module, configured to determine at least one second time based on at least one sensor historical time difference and the first time.

[0031] A third acquisition module 240, configured to acquire third state information of at least one target object, where the third state information corresponds to a third time.

[0032] A fourth acquisition module 250, configured to determine at least one fourth time based on the third state information, where the fourth time refers to a time when at least one target object may have an abnormality.

[0033] A stimulation parameter determination module 260, configured to determine a stimulation parameter based on at least one second time and at least one fourth time, where the stimulation parameter includes a target time and a stimulation amplitude.

[0034] In some embodiments, the stimulation parameter determination module 260 includes: a sensor sorting module, configured to sort at least one second time according to the likelihood of sensor abnormality to obtain a sensor time sequence; an object sorting module, configured to sort at least one fourth time according to the likelihood of object abnormality and the order of the fourth times to obtain an object time sequence; a delay determination module, configured to determine the delay of the sensor state according to the number of at least one second time based on a first preset relationship; an extended range determination module, configured to determine an extended time range for each fourth time based on the sensor time sequence, the object time sequence, and the delay of the sensor state; and a time determination module, configured to determine a part of the second times located within the extended time range of the fourth time, and remove the part of the second times from the sensor time sequence to obtain at least one target time and a target time sequence.

[0035] In some embodiments, the object anomaly prediction model includes a second state determination layer and a second anomaly determination layer. The stimulation parameter determination module 260 includes: a target state determination module, configured to predict the predicted target state information of at least one target object at a target time through the second state determination layer based on a third time, third state information, a target time, a corresponding work arrangement plan, and environmental data; a target anomaly determination module, configured to determine the target anomaly possibility of the object having an anomaly at the target time through the second anomaly determination layer based on the predicted target state information; a stimulation amplitude determination module, configured to determine a stimulation amplitude based on the target anomaly possibility and a second preset relationship; and a stimulation intensity determination module, configured to determine a stimulation intensity based on the stimulation amplitude.

[0036] A stimulation state determination module 270, configured to determine the stimulation state information of at least one sensor based on the stimulation parameters.

[0037] A command determination module 280, configured to determine a maintenance command based on the actual state information and the stimulation state information.

[0038] Figure 3 is an exemplary flowchart of a remote control method for an industrial sensor according to some embodiments of this specification. In some embodiments, the process 300 may be executed by a processor. As Figure 3 shown, the process 300 includes the following steps:

[0039] Step 310, determine at least one sensor and a corresponding target object.

[0040] In the deployment environment of the industrial sensor, there are distributed at least one sensor and at least one target object. A sensor is a device for monitoring, measuring, and collecting environmental parameters or device states. The target object is the specific object or system monitored by the sensor, which may be a machine device, a production line, an environmental condition, etc.

[0041] Step 320, obtain the first state information of at least one sensor, where the first state information corresponds to a first time.

[0042] The state information may refer to information related to the working state. The first state information may be working data related to the working state of at least one sensor at the first time. The first state information may include the response speed of the sensor, the amount of output data, etc. Based on the first state information, it can be determined whether the state information of at least one sensor is normal. The first time may refer to the current time. At least one sensor is used to determine the state information of at least one target object. The state information may be obtained by extraction and calculation of the data in the working log of the sensor.

[0043] Step 330, determine at least one second time based on the first state information.

[0044] The second time may refer to the time when at least one sensor may malfunction. The second time may be later than the second time, and the second time may refer to a future time. The number of second times may be at least one.

[0045] In some embodiments, determining at least one second time based on the first state information includes:

[0046] S11. Determine a first state information vector based on the first state information. The elements in the first state information vector may include the first time, sensor model, service life, and first state information.

[0047] S12. Determine at least one historical first state information vector through the sensor state information vector database based on the first state information vector. The sensor state information vector database may be preset manually based on historical data, which includes at least one historical sensor state information vector. The elements in each historical sensor state information vector include sensor model, service life, historical sensor state information, whether the sensor is faulty, etc.

[0048] The historical first state information vector may be a historical vector whose similarity to the first state information vector exceeds the first threshold. The vector similarity may be determined by formulas such as cosine similarity, Euclidean distance, and Manhattan distance. The first threshold may be set manually.

[0049] With the help of the state information vector database, historical similar state information vectors can be obtained for comparison and analysis with the current state, and the accuracy of analyzing the current state can be improved based on historical data.

[0050] S13. Determine at least one historical first time based on at least one historical first state information vector.

[0051] The historical first time refers to the time corresponding to the historical first state information vector.

[0052] S14. Determine at least one historical second state information based on at least one historical first time and historical first state information vector.

[0053] The historical second state information may refer to the state information corresponding to the nearest malfunction of the sensor to the historical first time.

[0054] S15. Determine at least one historical second time based on at least one historical second state information.

[0055] The time corresponding to the historical second state information is used as the historical second time, and the historical second time is later than the corresponding historical first time.

[0056] S16. Determine at least one sensor historical time difference based on at least one pair of corresponding historical first time and historical second time.

[0057] Use the time difference between the historical first time and the historical second time as the sensor historical time difference.

[0058] S17. Determine at least one second time based on at least one sensor historical time difference and the first time.

[0059] Add the sensor historical time difference to the first time as the second time. The number of sensor historical time differences can be the same as the number of second times.

[0060] For example, if the first time is 8:00, the historical first time corresponding to the historical first state information vector is 9:00, and the historical second time is 9:30, then the sensor historical time difference is 30 minutes, and the second time is 8:30.

[0061] Through the historical data and state information of the sensor itself, by using the historical state information and time data, and by comparing and analyzing the changes in the state information, the operating state of the sensor can be initially judged, and the future state change trend can be predicted.

[0062] Step 340. Obtain the third state information of at least one target object, where the third state information corresponds to the third time.

[0063] The third state information can be working data related to the working state of at least one target object at the first time. The third state information can include the current, voltage, temperature, etc. of the target object. The third state information of the target object can be obtained through the sensor. Based on the third state information, it can be judged whether the state of at least one target object is normal. The third time can be the same as the first time.

[0064] Step 350. Determine at least one fourth time based on the third state information.

[0065] The fourth time can refer to the time when at least one target object may have an abnormality. The fourth time can be later than the third time. The fourth time can refer to a future time. The number of fourth times can be at least one.

[0066] In some embodiments, determining at least one fourth time based on the third state information includes:

[0067] S21. Determine a third state information vector based on the third state information.

[0068] The elements in the third state information vector can include the third time, object model, object service life, and third state information. The object can refer to the monitored object of the sensor.

[0069] S22. Determine at least one historical third state information vector through the object state information vector database.

[0070] The object state information vector database can be artificially preset based on historical data, including at least one historical object state information vector. The elements in each historical object state information vector include object model, object service life, historical object state information, whether the object is faulty, etc. The historical third state information vector can be a historical vector whose similarity to the third state information vector exceeds the second threshold. The second threshold can be determined manually.

[0071] S23. Determine at least one historical third time based on at least one historical third state information vector.

[0072] The historical third time refers to the time corresponding to the historical third state information vector.

[0073] S24. Determine at least one historical fourth state information based on at least one historical third time and the historical third state information vector.

[0074] S25. Determine at least one historical fourth time based on at least one historical fourth state information.

[0075] S26. Determine at least one object historical time difference based on at least one pair of corresponding historical third time and historical fourth time.

[0076] S27. Determine at least one fourth time based on at least one object historical time difference and the third time.

[0077] For similar content, refer to the relevant content of determining at least one second time in step 330.

[0078] Through the historical data and state information of the target object itself, historical state information and time data are utilized. By comparing and analyzing the changes in state information, the operating state of the target object can be preliminarily judged, and the future state change trend can be predicted.

[0079] Step 360. Determine the stimulation parameter based on at least one second time and at least one fourth time.

[0080] The stimulation parameter can refer to the parameter for stimulating the target object. The stimulation parameter can include the target time and the stimulation intensity. Through the stimulation parameter, the working state information of the target object can be changed, and then it can be checked whether the sensor can detect whether the working state of the target object has changed to determine whether the sensor is abnormal.

[0081] The target time may refer to the stimulation start time in the stimulation parameters. The number of target times may be at least one. In some embodiments, the stimulation intensity is determined by the stimulation increase. The stimulation increase may be the change amplitude of the state of the target object such as current, voltage, temperature, etc. The stimulation parameters may determine a stimulation sequence based on the target time and the corresponding stimulation increase. In some embodiments, the stimulation parameters may be a sequence of stimulation parameters with respect to time.

[0082] At the target time, if the sensor output data is still abnormal, it is very likely that there is a problem with the sensor itself rather than caused by the target object. And because there are many stimulation start times in the stimulation parameters, the amount of data about the state of the target object that the sensor needs to acquire and upload increases sharply, which will affect the response speed of the sensor and the amount of output data, and further affect the generation of commands.

[0083] In some cases, the abnormal output data of the sensor may be due to a problem with the sensor or a problem with the target object. By excluding at least one fourth time from at least one second time to obtain the target time, based on the target time, it is highly probable to exclude the abnormal output data of the sensor caused by the abnormal target object.

[0084] In some embodiments, the number of at least one second time and the number of at least one fourth time can be determined, and the time that coincides with the fourth time is removed from the second time to obtain the target time.

[0085] When the number of second times is too large, or the coincidence degree between the fourth time and the second time is not high, resulting in too many target times, which affects the response speed of the sensor and the amount of output data. In some embodiments, the target time can be determined through the following steps:

[0086] S31, sort at least one second time according to the sensor abnormality possibility (from high to low) to obtain a sensor time series.

[0087] In some embodiments, the sensor abnormality possibility can be determined by a sensor abnormality prediction model. The sensor abnormality prediction model can be a machine learning model, a bidirectional long short-term memory network (LSTM). The sensor abnormality prediction model may include a first state determination layer and a first abnormality determination layer. The sensor abnormality prediction model can be trained by historical data samples.

[0088] In some embodiments, based on the first time, the first state information, the second time, the corresponding work arrangement plan, and the environmental data, the first state determination layer predicts the predicted second state information of at least one sensor at the second time, and based on the predicted second state information, the first abnormality determination layer determines the sensor abnormality possibility of the sensor occurring abnormality at the second time.

[0089] Among them, the work plan arrangement can be obtained from the factory's annual plan, monthly plan, etc.

[0090] S32. Sort at least one fourth time according to the object anomaly possibility and the order of the fourth time to obtain an object time series.

[0091] In some embodiments, different weights can be set for the object anomaly possibility and the order of the fourth time, score at least one fourth time based on the weights, and determine the object time series based on the scores.

[0092] By sorting the second time and the fourth time, important time nodes can be placed in the front, reducing the impact on the sensor response speed. Doing so also helps to screen out the most important time points from a large amount of time, reduce redundant data, and improve data processing efficiency.

[0093] In some embodiments, the object anomaly possibility can be determined through an object anomaly prediction model. The object anomaly prediction model can be a machine learning model, a bidirectional long short-term memory network (LSTM). The object anomaly prediction model can include a second state determination layer and a second anomaly determination layer. The object anomaly prediction model can be trained through historical data samples.

[0094] In some embodiments, based on the third time, the third state information, the fourth time, the corresponding work arrangement plan, and the environmental data, the second state determination layer predicts the predicted fourth state information of at least one target object at the fourth time, and based on the predicted fourth state information, the second anomaly determination layer determines the object anomaly possibility of the object having an anomaly at the fourth time.

[0095] The anomaly prediction model will consider historical data and the relationship with time to predict the anomaly possibility within a future period of time.

[0096] S33. Determine the delay of the sensor state according to the number of at least one second time based on the first preset relationship.

[0097] The first preset relationship can be the relationship between the number of time points and the delay. The first preset relationship can be preset manually. Since it is necessary to increase the stimulus sequence and the sensor needs to acquire and upload the state information of the target object at the stimulus time, when the number of stimulus time points increases, the state information that needs to be acquired and uploaded increases, which will inevitably cause a delay in the sensor state.

[0098] S34. Determine the extended time range of each fourth time based on the sensor time series, the object time series, and the delay of the sensor state.

[0099] In some embodiments, based on the delay of the sensor state, the quantity of the second time, and the quantity of the fourth time, the extended amplitude of the fourth time is determined through an extended amplitude model, and the extended time range of each fourth time is determined based on the extended amplitude.

[0100] The extended amplitude may refer to the amplitude of the extension of the fourth time. The extended amplitude can extend each fourth time into a time range, increasing the quantity of the second time falling within the extended range of the fourth time, thereby effectively reducing the quantity of the second time and the data volume of the target time. For example, if the fourth time is 9:00 and the extended amplitude is 2 minutes, the extended time range is (8:58, 9:02).

[0101] The extended amplitude model may be a machine learning model, such as a deep neural network. The extended amplitude model can be obtained through training with historical data samples.

[0102] The extended amplitude model includes a data comparison layer and an amplitude determination layer. The sensor time series and the object time series are input into the data comparison layer, and the output is the time similarity. The time similarity and the delay of the sensor state are input into the amplitude determination layer, and the output is the extended amplitude of the fourth time.

[0103] When the time similarity is higher, it indicates that the time points of the anomalies of the sensor and the target object are very similar. The quantity of the target time obtained by removing the fourth time from the second time is very small, so the delay impact on the sensor response speed based on the target time is very small, and the extended amplitude of the fourth time should be set smaller. When the delay of the sensor state is larger, it indicates that the quantity of the second time is too large. If appropriate quantities of stimulation parameters are to be obtained, the extended amplitude of the fourth time needs to be set larger.

[0104] Through some embodiments of this specification, the sensor time series and the object time series are time series considering the anomaly possibility, and the extended amplitude can be determined more accurately.

[0105] In some embodiments, the extended amplitude of each fourth time may be different. In some embodiments, for each fourth time, the second time with the highest similarity to each fourth time can be determined first, and the corresponding extended amplitude can be determined through a machine learning model based on the anomaly possibility of the selected second time and the corresponding fourth time in their time series. For example, the second time T4 is the most similar to the fourth time t2, and t2 is in the second position of the object time series, indicating that it is very likely that the object has an anomaly at t2. The extended amplitude of t2 needs to be increased so that T4 falls within the extended range and T4 is removed from the target time. If the ranking of the fourth time is relatively posterior, the extended amplitude can be appropriately reduced.

[0106] S35. Determine a partial second time within the extended time range at the fourth time, and remove the partial second time from the sensor time series to obtain at least one target time and a target time series.

[0107] When the sensor output data is abnormal, it may be a problem with the sensor itself or a problem with the monitored target object. By excluding at least one fourth time from at least one second time to obtain the target time, that is, by excluding the possibility of the target object being abnormal from the time point when the sensor fails.

[0108] In some embodiments, the stimulation intensity of each target time can be determined by an object abnormality prediction model:

[0109] Based on the third time, the third state information, the target time, the corresponding work arrangement plan, and the environmental data, predict the predicted target state information of at least one target object at the target time through the second state determination layer, and determine the target abnormality possibility of the object being abnormal at the target time through the second abnormality determination layer based on the predicted target state information. Determine the stimulation increase based on the target abnormality possibility and the second preset relationship. The second preset relationship can be set manually.

[0110] The work arrangement plan can refer to the arrangement of work parameters at the corresponding time. In some embodiments, the corresponding work arrangement plan can refer to the arrangement of work parameters at the third time and the target time. In some embodiments, add / reduce the corresponding stimulation increase to the work arrangement plan at the target time to obtain the stimulation intensity. By adding the corresponding work arrangement plan during input, it can be considered that even if the planned work parameters at the target time are increased significantly, it will not be a stimulation increase that can cause abnormalities.

[0111] Step 370. Determine the stimulation state information of at least one sensor based on the stimulation parameters.

[0112] In some embodiments, the normal state of the target object under the stimulation sequence can be determined based on the stimulation sequence and the target object model through a third preset relationship.

[0113] The normal state can be the work parameters of the target object working normally based on the stimulation parameters at the target time. The normal state can include the range of each work parameter, such as the range of current, the range of voltage, etc. The third preset relationship can be the corresponding relationship between the stimulation sequence and the work parameters of the target object in the normal state.

[0114] In some embodiments, determine the stimulation state based on the normal state, the sensor abnormality possibility, the stimulation parameters, and the target time.

[0115] The stimulation state can refer to the state of the sensor obtaining the state information of the target object under sensor abnormality.

[0116] Step 380: Determine a maintenance order based on the actual status information and the stimulation status information.

[0117] The actual status information may refer to the status information of the target object obtained by the sensor at the target time point under actual circumstances, and may include the current, voltage, temperature, etc. of the target object. In some embodiments, the actual status information can be obtained directly from the sensor immediately.

[0118] In some embodiments, the actual status information can be predicted by a status prediction model.

[0119] Predict the actual status information of at least one sensor at the target time through the status prediction model based on the first time, the first status information, the stimulation sequence, and the environmental data. In some embodiments, if the actual status information exceeds the stimulation status information, determine the maintenance order through a preset status-maintenance relationship.

[0120] Merely based on the abnormality of the sensor working status, it is impossible to accurately determine whether the abnormality is caused by the fault of the sensor itself. Through some embodiments of this specification, according to the prediction of its own data and external stimuli, the accuracy of judging the sensor status can be improved, and further, the sensor status can be adjusted or intervened through maintenance to cope with expected abnormal situations and ensure the normal operation of the system.

[0121] It should be noted that different embodiments may produce different beneficial effects. In different embodiments, the possible beneficial effects may be any one or several combinations of the above, or any other possible beneficial effects that can be obtained.

[0122] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only an example and does not constitute a limitation to this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are suggested in this specification, so such modifications, improvements, and corrections still fall within the spirit and scope of the exemplary embodiments of this specification.

[0123] At the same time, this specification uses specific terms to describe the embodiments of this specification. Such as "one embodiment", "an embodiment", and / or "some embodiments" mean a certain feature, structure, or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "an embodiment" or "one embodiment" or "an alternative embodiment" mentioned twice or more at different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures, or characteristics in one or more embodiments of this specification can be combined appropriately.

[0124] In addition, unless clearly stated in the claims, the order of elements and sequences, the use of numerical and alphabetical characters, or the use of other names in this specification are not used to limit the order of the processes and methods in this specification. Although some currently useful embodiments are discussed through various examples in the above disclosure, it should be understood that such details are for illustrative purposes only. The appended claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that conform to the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only through software solutions, such as installing the described system on existing processors or mobile devices.

[0125] Similarly, it should be noted that, in order to simplify the presentation of the disclosure in this specification and thus help the understanding of one or more embodiments, in the foregoing description of the embodiments of this specification, sometimes multiple features are merged into one embodiment, drawing, or description thereof. However, this method of disclosure does not mean that the features required by the subject matter of this specification are more than those mentioned in the claims. In fact, the features of the embodiments are fewer than all the features of the individual embodiments disclosed above.

[0126] In some embodiments, numbers are used to describe components and the quantity of attributes. It should be understood that such numbers used for the description of embodiments are modified by the modifiers "about", "approximate" or "substantially" in some examples. Unless otherwise stated, "about", "approximate" or "substantially" indicate that the number allows a variation of ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, and such approximate values may change according to the characteristics required by individual embodiments. In some embodiments, the numerical parameters should consider the specified significant digits and adopt the method of retaining general digits. Although the numerical ranges and parameters used in some embodiments of this specification to confirm the breadth of their scope are approximate values, in specific embodiments, the setting of such numerical values is as precise as possible within the feasible range.

[0127] For each patent, patent application, patent application publication, and other materials cited in this specification, such as articles, books, specifications, publications, documents, etc., their entire contents are hereby incorporated into this specification by reference. This excludes the application history files that are inconsistent with or conflict with the content of this specification, and also excludes the files that limit the broadest scope of the claims of this specification (currently or subsequently appended to this specification). It should be noted that if there are inconsistencies or conflicts between the descriptions, definitions, and / or uses of terms in the supplementary materials of this specification and the content of this specification, the descriptions, definitions, and / or uses of terms in this specification shall prevail.

[0128] Finally, it should be understood that the embodiments in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, by way of example and not limitation, alternative configurations of the embodiments of this specification may be regarded as consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly presented and described in this specification.

Claims

1. A remote control method for an industrial sensor, characterized in that: include: determining at least one sensor and a corresponding target object; Acquire first state information of the at least one sensor, where the first state information corresponds to a first time; Determine at least one second time based on the first state information, where the second time refers to a time when at least one sensor may be abnormal; Acquire third state information of at least one of the target objects, where the third state information corresponds to a third time; Determine at least one fourth time based on the third state information, where the fourth time refers to a time when an abnormality may occur in at least one target object; determining stimulation parameters based on the at least one second time and the at least one fourth time, the stimulation parameters comprising a target time and a stimulation intensity; determining stimulation state information of at least one sensor based on the stimulation parameters; determining a maintenance command based on the actual state information and the stimulus state information; Wherein, determining the target time includes: sorting the at least one second time according to the possibility of sensor abnormality to obtain a sensor time series; Sorting the at least one fourth time according to the abnormal possibility of the object and the order of the fourth time to obtain an object time sequence; determining a delay of at least one second amount of time to the sensor state according to a first preset relationship; determining an extended time range of each fourth time based on the sensor time series, the object time series, and the delay of the sensor state; Determine a portion of the second time that is within the extended time range of the fourth time, remove the portion of the second time from the sensor time series, and obtain at least one target time and a target time series; The object abnormality prediction model includes a second state determination layer and a second abnormality determination layer, and determining the stimulus intensity through the object abnormality prediction model includes: Predicting predicted target state information of at least one target object at the target time through the second state determination layer based on the third time, the third state information, the target time, the corresponding work schedule and the environmental data; Determining a target abnormality possibility that an abnormality occurs in the object at the target time through the second abnormality determination layer based on the predicted target state information; Determining a stimulation increase based on the target abnormality probability and a second preset relationship; The stimulation intensity is determined based on the stimulation increase.

2. The remote control method of an industrial sensor according to claim 1, characterized in that: Determining at least one second time based on the first state information includes: determining a first state information vector based on the first state information; Determine at least one historical first state information vector through a sensor state information vector database based on the first state information vector; determining at least one historical first time based on the at least one historical first state information vector; Determine at least one historical second state information based on the at least one historical first time and the historical first state information vector; determining at least one historical second time based on the at least one historical second state information; determining at least one sensor historical time difference based on at least one pair of corresponding historical first times and historical second times; The at least one second time is determined based on the at least one sensor historical time difference and the first time.

3. A remote control system for an industrial sensor, characterized in that: include: A relationship determination module, used to determine at least one sensor and a corresponding target object; A first acquisition module, configured to acquire first state information of the at least one sensor, wherein the first state information corresponds to a first time; A second acquisition module, configured to determine at least one second time based on the first state information, where the second time refers to a time when at least one sensor may be abnormal; A third acquisition module, used to acquire third state information of the at least one target object, wherein the third state information corresponds to a third time; A fourth acquisition module, configured to determine at least one fourth time based on the third state information, wherein the fourth time refers to a time when an abnormality may occur in at least one target object; A stimulation parameter determination module, configured to determine stimulation parameters based on the at least one second time and the at least one fourth time, wherein the stimulation parameters include a target time and a stimulation intensity; A stimulation state determination module, configured to determine stimulation state information of at least one sensor based on the stimulation parameters; A command determination module, used for determining a maintenance command based on the actual state information and the stimulus state information; Wherein, the stimulation parameter determination module includes: A sensor sorting module, used to sort the at least one second time according to the possibility of sensor abnormality to obtain a sensor time series; An object sorting module, used to sort the at least one fourth time according to the object abnormality possibility and the order of the fourth time to obtain an object time sequence; a delay determination module, configured to determine a delay of at least one second time amount to a sensor state according to a first preset relationship; an extended range determination module, configured to determine an extended time range of each fourth time based on the sensor time series, the object time series, and a delay of the sensor state; a time determination module, configured to determine a portion of the second time within an extended time range of the fourth time, and remove the portion of the second time from the sensor time sequence to obtain at least one target time and a target time sequence; The object abnormality prediction model includes a second state determination layer and a second abnormality determination layer, and the stimulation parameter determination module includes: a target state determination module, configured to predict predicted target state information of at least one target object at the target time through the second state determination layer based on the third time, the third state information, the target time, a corresponding work schedule and environmental data; A target anomaly determination module, configured to determine the target anomaly possibility that the object will be abnormal at the target time through the second anomaly determination layer based on the predicted target state information; A stimulation increase determination module, used to determine the stimulation increase based on the target abnormality possibility and a second preset relationship; A stimulation intensity determination module is used to determine the stimulation intensity based on the stimulation increase.

4. The remote control system of the industrial sensor according to claim 3, characterized in that: The second acquisition module includes: a vector determination module, configured to determine a first state information vector based on the first state information; a historical first state determination module, configured to determine at least one historical first state information vector through a sensor state information vector database based on the first state information vector; a historical first time determination module, configured to determine at least one historical first time based on the at least one historical first state information vector; A historical second state determination module, configured to determine at least one historical second state information based on the at least one historical first time and the historical first state information vector; a historical second time determination module, configured to determine at least one historical second time based on the at least one historical second state information; A time difference determination module, configured to determine at least one sensor historical time difference based on at least one pair of corresponding historical first time and historical second time; The second time acquisition module is used to determine the at least one second time based on the at least one sensor historical time difference and the first time.

5. A remote control device for an industrial sensor, characterized in that: The apparatus comprises at least one processor and at least one memory; The at least one memory is used to store computer instructions; The at least one processor is used to execute at least part of the computer instructions to implement the remote control method of the industrial sensor as described in any one of claims 1 to 2.

6. A computer-readable storage medium, characterized in that: The storage medium stores computer instructions, and when the computer instructions are executed by the processor, the remote control method of the industrial sensor according to any one of claims 1 to 2 is implemented.

Images