Equipment operation data acquisition and processing system based on intelligent sensor

Abstract

The invention discloses an equipment operation data acquisition and processing system based on intelligent sensors, relates to the technical field of industrial internet, and solves the technical problem that the accuracy of acquired data is insufficient due to the fact that mutual influence among the intelligent sensors cannot be considered during data acquisition in the prior art. The method comprises the steps of analyzing mutual influence among a plurality of intelligent sensors through an artificial intelligence model; acquiring a plurality of equipment operation data of the target equipment through a plurality of set intelligent sensors, taking the equipment operation data as basic data in sequence, and extracting an influence prediction model based on the basic data; correcting the basic data based on the influence prediction model; the set simulation rule simulates the operation of each intelligent sensor in the equipment, the data training set is constructed to train and obtain the influence prediction model, the influence prediction model can identify the mutual influence between the intelligent sensors, the mutual influence is eliminated after the basic data is corrected, and the accuracy of data acquisition is improved.

Description

Technical Field

[0001] This application belongs to the technical field of industrial Internet, and specifically relates to a device operation data acquisition and processing system based on intelligent sensors. Background Art

[0002] In the industrial Internet, a large amount of industrial data generated during the operation of devices is timely collected and extracted by intelligent sensors. These industrial data are used to evaluate the operation status of devices, and the status of devices can also be predicted based on the collected historical data. Therefore, device operation data is very important in the industrial Internet.

[0003] Currently, in the device operation data acquisition solutions based on intelligent sensors, the following problems mainly exist: 1) The sampling frequencies of different intelligent sensors are different, resulting in the data collected by them not being time-aligned. If the data is not time-aligned, it will affect the evaluation accuracy of the device status; 2) When intelligent sensors collect device operation data, they are easily affected by the environment and other sensors. If the data is not corrected, the true operation status of the device cannot be analyzed.

[0004] This application provides a device operation data acquisition and processing system based on intelligent sensors to solve the above technical problems. Summary of the Invention

[0005] This application aims to solve at least one of the technical problems existing in the prior art; for this purpose, this application proposes a device operation data acquisition and processing system based on intelligent sensors, which is used to solve the technical problem that the prior art cannot consider the mutual influence between intelligent sensors during data acquisition, resulting in insufficient accuracy of the collected data.

[0006] To achieve the above object, the first aspect of this application provides a device operation data acquisition and processing system based on intelligent sensors, including a cloud platform and an edge acquisition layer connected thereto; Edge Acquisition Layer: It is used to collect a number of device operation data of the target device through a number of set intelligent sensors; where the device operation data refers to the data related to the operation status of the target device; and, Successively take a number of device operation data as basic data, extract an influence prediction model based on the basic data; correct the basic data based on the influence prediction model to obtain target data; Cloud Platform: It is used to analyze the mutual influence between a number of intelligent sensors through an artificial intelligence model to obtain an influence prediction model; and, It is used to receive a number of target data and perform interpolation processing on the number of target data to achieve alignment of the number of target data.

[0007] Preferably, the mutual influence between several intelligent sensors is analyzed through an artificial intelligence model, including: Extract simulation training data; wherein, the simulation training data is obtained through the setting and operation modes of several intelligent sensors in the simulation device; Train the artificial intelligence model constructed through the simulation training data, and mark the trained artificial intelligence model as an influence prediction model; wherein, the artificial prediction model includes a BP neural network model or an RBF neural network model.

[0008] Preferably, the acquisition of the simulation training data includes: Determine several intelligent sensors set in the device, and sequentially use the intelligent sensors as target sensors; mark the other intelligent sensors except the target sensor as non-target sensors; Detect the detection data of the target sensor during the operation of the device, and mark it as the first target data; then simulate the detection data of the target sensor when the non-target sensors operate normally according to the simulation rules, and mark it as the second target data; Generate a simulation training data from the change ratio between the second target data and the first target data, and the corresponding simulation rules; wherein, the simulation rules are used to represent whether the non-target sensors are operating.

[0009] Preferably, the acquisition of the simulation rules includes: Mark the operating states of the non-target sensors to obtain a marking group; wherein, the operating states include operating and not operating; Each time, extract a mark from the marking group of each non-target sensor, and integrate the extracted marks into a simulation rule. After several extractions, several simulation rules are obtained.

[0010] Preferably, the correction of the basic data based on the influence prediction model includes: Extract the influence prediction model corresponding to the intelligent sensor of the basic data, and the operating states of other intelligent sensors during the acquisition of the basic data; Preprocess according to the operating states of other intelligent sensors and then input them into the influence prediction model to obtain a change ratio; correct the basic data based on the change ratio.

[0011] Preferably, the interpolation processing of several target data includes: Extract several target data, and determine the target time for which interpolation processing is required according to the several target data; Obtain the target data at the target time through interpolation processing.

[0012] Preferably, determining the target time for which interpolation processing is required according to several target data includes: Taking the acquisition moment corresponding to any target data as the judgment moment, calculate the quantity of target data corresponding to the judgment moment; Judge whether the quantity of target data is consistent with the quantity of intelligent sensors; if so, interpolation processing is not required at the judgment moment; if not, the judgment moment is taken as the target moment.

[0013] Preferably, determining the target moment that requires interpolation processing based on a number of target data includes: Select the intelligent sensor with the worst stability based on the target data and mark it as the reference sensor; take the acquisition moment of the target data corresponding to the reference sensor as the judgment moment; Calculate the quantity of target data corresponding to the judgment moment; judge whether the quantity of target data is consistent with the quantity of intelligent sensors; if so, interpolation processing is not required at the judgment moment; if not, the judgment moment is taken as the target moment.

[0014] Preferably, selecting the intelligent sensors with relatively poor stability based on the target data includes: Construct a data fluctuation curve from the target data of a number of intelligent sensors; Based on the data fluctuation curve, take the intelligent sensor with the worst stability as the reference sensor.

[0015] Preferably, after determining the target moment, identify the intelligent sensor corresponding to the missing data at the target moment; perform interpolation processing based on the target data collected by this intelligent sensor to obtain the target data at the target moment.

[0016] Compared with the prior art, the beneficial effects of this application are: 1. This application analyzes the mutual influence between a number of intelligent sensors through an artificial intelligence model to obtain an influence prediction model; after a number of intelligent sensors are set to collect a number of device operation data of the target device, the a number of device operation data are sequentially used as basic data, and the influence prediction model is extracted based on the basic data; the basic data is corrected based on the influence prediction model to obtain target data; the simulation rules set in this application simulate the operation of each intelligent sensor in the device, construct a data training set to train the influence prediction model, and the influence prediction model can identify the mutual influence between the intelligent sensors, eliminate this mutual influence after correcting the basic data, and improve the accuracy of data collection.

[0017] 2. In this application, the cloud platform receives a number of target data and performs interpolation processing on the number of target data to achieve alignment of the number of target data. Specifically, it first determines the data stability of the target data collected by each intelligent sensor, and selects the one with the worst stability as the reference sensor. If the data stability is poor, the interpolation accuracy is low. Therefore, through the solution of this embodiment, the accuracy of the interpolation result can be ensured. After interpolation, the acquisition time corresponding to each target data in the cloud platform includes the target data of all other intelligent sensors, realizing the alignment of data in time to save the data processing time during subsequent device evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0019] Figure 1 It is a schematic diagram of the method steps of the device operation data acquisition and processing system in the first embodiment of the present application; Figure 2 It is a schematic diagram of the system principle of the device operation data acquisition and processing system in the first embodiment of the present application; Figure 3 It is a schematic diagram of the method steps of data stability judgment in the second embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0020] The following will clearly and completely describe the technical solutions of the present application in combination with the embodiments. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0021] An intelligent sensor is a sensor with information processing functions, which integrates a sensitive element, a microprocessor, and a communication interface, and can realize data acquisition, processing, and transmission. An intelligent sensor not only has the basic functions of a traditional sensor, but also has intelligent features such as self-calibration, self-diagnosis, and self-adaptation, which can improve the measurement accuracy and reliability and adapt to complex industrial environments.

[0022] Due to the above advantages, intelligent sensors have been widely used in the industrial Internet. Intelligent sensors are less affected by the environment due to their intelligent characteristics. However, there are a large number of devices in the industrial Internet, and the deployment of intelligent sensors is relatively complex. It is impossible to calibrate the impact of devices on intelligent sensors by pre-built calibration models, which may cause intelligent sensors to be easily affected by other devices, or even other intelligent sensors during operation, resulting in inaccurate acquisition results of intelligent sensors and affecting the evaluation and prediction of device status.

[0023] In order to calibrate the impact of other devices on intelligent sensors, the present application designs the following technical solutions to solve the above technical problems. Embodiment

[0024] Please refer to Figure 1 - Figure 2 , an embodiment of the first aspect of the present application provides a device operation data acquisition and processing system based on an intelligent sensor, including a cloud platform and an edge acquisition layer connected thereto; Edge acquisition layer: used to collect a number of device operation data of the target device through a number of set intelligent sensors; wherein, the device operation data refers to data related to the operation state of the target device; and, successively take a number of device operation data as basic data, extract an influence prediction model based on the basic data; correct the basic data based on the influence prediction model to obtain target data; Cloud platform: used to analyze the mutual influence between a number of intelligent sensors through an artificial intelligence model to obtain an influence prediction model; and, used to receive a number of target data and perform interpolation processing on the number of target data according to the influence prediction model to achieve alignment of the number of target data.

[0025] The device operation data acquisition and processing system in this embodiment mainly includes a cloud platform and a data acquisition layer. The data acquisition layer is mainly responsible for data acquisition and standardization processing. Data processing through the data acquisition layer can reduce the pressure on the cloud platform and improve the fluency of the entire system. The main work of the data acquisition layer is to collect data related to device operation through the set intelligent sensors, including but not limited to temperature, vibration, oil level, displacement, etc., and after standardizing the collected data, send it to the cloud platform. Standardization processing includes unifying data formats, transmission protocols, etc.

[0026] One of the tasks of the cloud platform is to train and obtain an influence prediction model, and send the influence prediction model to the data acquisition layer to further correct the collected basic data; the second task is to perform time alignment on the received target data to provide qualified data for subsequent device status evaluation and prediction and improve efficiency.

[0027] The intelligent sensor itself has a certain data calibration ability. For example, in response to changes in the temperature and humidity of the device's environment, it can calibrate the data through a built-in calibration model to eliminate the impact of environmental changes on the data acquisition results. However, when deploying other intelligent sensors, it is inevitable to lay some data transmission lines. These data transmission lines will generate signal interference on the surrounding area when transmitting signals, and some intelligent sensors will also generate signal interference on the surrounding area during operation. These interferences cannot be calibrated by the built-in calibration model when the intelligent sensor leaves the factory.

[0028] Exemplarily, the interferences suffered by intelligent sensors during operation mainly include electromagnetic interference, signal crosstalk, etc. Electromagnetic interference is mainly caused by the internal electronic components of some intelligent sensors generating electromagnetic radiation during operation. For example, high-frequency signal cables will generate an electromagnetic field during operation, and this electromagnetic field will interfere with nearby intelligent sensors, especially magnetosensitive sensors, capacitive sensors, inductive sensors, etc. that are more sensitive to the electromagnetic field are easily affected. Signal crosstalk mainly occurs when multiple intelligent sensors are installed adjacent to or opposite each other. In this case, co-frequency interference may occur, such as ultrasonic sensors may experience this interference.

[0029] Furthermore, the intelligent sensors on the device mainly provide data for the device user. Therefore, the installation location and installation method of the intelligent sensors are not fixed, mainly considering the convenience of the device user. If there are many intelligent sensors installed and they are close to each other, it is very likely to generate mutual interference, thus affecting the data accuracy. Moreover, due to the flexibility of the installation location and installation method, calibration cannot be performed through a pre-set calibration model.

[0030] In this embodiment, to solve the above problems, after determining the device location and installation method, intelligent sensors are set for each device. Then, the operation of the intelligent sensors is simulated through simulation rules to obtain sufficient simulation training data, and an artificial intelligence model is trained with this simulation training data. The trained artificial intelligence model then contains the mapping relationship between the different operating states of other intelligent sensors and the measurement results of the target sensor.

[0031] During the actual operation process, after the intelligent sensor collects the basic data, it can be determined whether other intelligent sensors have an impact during the collection of the basic data through the corresponding mapping relationship of this intelligent sensor. If there is an impact, the change ratio is combined with the basic data to complete data correction and obtain the target data. This target data is the data after eliminating the impact of other intelligent sensors.

[0032] It should be noted that intelligent sensors are not only affected by other intelligent sensors, but also by other devices. That is, the operating states of other devices can be introduced into the simulation rules to identify the data errors of intelligent sensors under the operating states of other intelligent sensors or other devices, so as to obtain more accurate target data.

[0033] One of the key points of the technical solution provided in this embodiment lies in how to construct an influence prediction model. Next, the construction method of the influence prediction model will be described in detail as follows: Before constructing the influence prediction model, simulations are first carried out to obtain simulation training data. The specific scheme can be referred to as follows: Determine several intelligent sensors set in the device, and sequentially use the intelligent sensors as the target sensors; Mark the other intelligent sensors except the target sensor as non-target sensors; Detect the detection data of the target sensor during the operation of the device and mark it as the first target data; Then, according to the simulation rules, simulate the detection data of the target sensor when the non-target sensors are operating normally and mark it as the second target data; Generate a piece of simulation training data from the change ratio between the second target data and the first target data, and the corresponding simulation rules.

[0034] First, it is necessary to determine several intelligent sensors set in the device, including the installation location, signal transmission method, etc. Before the device officially works, simulations are carried out on it to obtain simulation training data. Specifically: Use one of the intelligent sensors as the target sensor, and the others except the target sensor as non-target sensors.

[0035] By marking the operating states of the non-target sensors, each non-target sensor corresponds to a marking group. In this marking group, the marks corresponding to the operating states, that is, both the operating state and the non-operating state each correspond to a mark.

[0036] Extract one mark from each non-target sensor, and splice the marks of all the extracted non-target sensors to form an array, which can be used as a simulation rule. Several simulation rules corresponding to each target sensor can be obtained through permutation and combination. Each simulation rule can be understood as the working state of other non-target sensors when the target sensor is working. In extreme cases, other non-target sensors may all not work, or may all work. It should be noted that in this embodiment, there is no correlation between the working states of the target sensor and the non-target sensors, and they all work independently, that is, whether any non-target sensor works or not will not affect the normal working of the target sensor.

[0037] Through the above scheme, the intelligent sensors are sequentially determined as the target sensors, and the simulation rules corresponding to the target sensors are determined through permutation and combination. Each target sensor corresponds to several simulation rules. By simulating the actual operating conditions of the intelligent sensors in the device through the simulation rules, basic data can be collected.

[0038] After setting the simulation rules for each intelligent sensor, each intelligent sensor is still used as the target sensor in sequence. Then, the target sensor and the corresponding device are controlled to operate. At the same time, the operating environment corresponding to the target sensor is simulated according to the simulation rules in sequence, and the detection data of the target sensor is collected in real time. In this way, each time the detection data corresponding to the target sensor in one working scenario of each non-target sensor can be collected, and then the corresponding simulation rule and detection data are integrated into one piece of simulation training data. Through this method, several pieces of simulation training data corresponding to the target sensor can be obtained, and then several pieces of simulation training data corresponding to each intelligent sensor can be obtained.

[0039] It should be noted that although multiple intelligent sensors will be set on the device according to needs, the number of them will not be particularly large, ranging from several to more than a dozen. Moreover, the operating state of the intelligent sensor can be controlled through the Internet of Things, the generation difficulty of the simulation rules is not high, and the actual simulation process is relatively simple, which will not bring a large amount of data processing. Furthermore, in order to provide sufficient simulation training data, the simulation rules can be combined with the operating state of the device to simulate the operating environment of the target sensor. The operating state of the device can be, for example, the preheating stage, the normal operating stage, or the operating years, etc.

[0040] After determining the simulation training data corresponding to several intelligent sensors through the above scheme, all the simulation training data can be integrated and used to train the artificial intelligence model. The specific training process can be referred to as follows: Obtain the simulation training data corresponding to each intelligent sensor, and insert the digital flag corresponding to the intelligent sensor into each piece of simulation training data. This digital flag is used to identify the target sensor to which the simulation training data belongs.

[0041] Then, the digital flag in each piece of simulation training data and the operating state of the non-target sensor corresponding to the simulation rule are preprocessed as the model input data; the change ratio of the detection data of the target sensor corresponding to the digital flag is preprocessed as the model output data. The above preprocessing is for inputting into the artificial intelligence model for training. It should be noted that the change ratio here is calculated from the detection data of the target sensor and the reference data when the non-target sensor operates under the simulation rule, and the calculation can be referred to as: (detection data - reference data) / reference data; the reference data is the detection data collected in real time by the target sensor when no other non-target sensors are operating.

[0042] According to the existing model training method, the constructed artificial intelligence model is trained through the model input data and the model output data, and an influence prediction model can be obtained. During the training process, the simulation training data is divided into a training set, a test set, and a validation set in proportion, and the proportion can be 5:3:2.

[0043] After the impact prediction model is obtained, it can be distributed to the data acquisition layer. After the data acquisition layer receives the basic data collected in real time by each intelligent sensor, it uses the impact prediction model to correct the basic data. The specific correction process can be referred to as follows; After the data acquisition layer obtains the basic data, it determines the device corresponding to the basic data, and then extracts the impact prediction model corresponding to the device. The intelligent sensor that collects the basic data is used as the target sensor, and the digital signature of the target sensor is identified. At the same time, according to the collection time of the basic data, it is determined whether other intelligent sensors are working at this collection time, that is, the operating states of other intelligent sensors are determined. The digital signature and the operating state reference model of other intelligent sensors are input into the data for processing, and the change ratio can be obtained by inputting it into the impact prediction model. The basic data can be corrected through this change ratio.

[0044] It should be noted that some intelligent sensors do not work continuously, but work according to the set sampling frequency. Therefore, when an intelligent sensor does not perform data collection, it can be considered that it will not affect other intelligent sensors, and its operating state can be determined as not running. Of course, if an intelligent sensor, even when not running, may affect other intelligent sensors due to its standby state, then the standby state of this intelligent sensor is also marked as the running state, and this principle is also referred to in the training process of the impact prediction model.

[0045] After correcting the basic data through the impact prediction model, the part of the basic data affected by other intelligent sensors can be removed, so as to obtain the data of the device itself, that is, the target data. When this target data is used to evaluate the operating state of the device subsequently, the accuracy of the evaluation result can be guaranteed.

[0046] After the data acquisition layer corrects and obtains the target data of each intelligent sensor, it sends the target data to the cloud platform. Since the sampling frequencies of the target data received by the cloud platform are different for each intelligent sensor, the target data cannot be aligned in time. If multi-source data fusion processing is required for device evaluation, the detection data of all intelligent sensors cannot be obtained at the same moment, and additional processing is required during device evaluation, which will waste a lot of time and the evaluation state of the device cannot be obtained in a timely manner.

[0047] An arbitrary target data can be selected, and the corresponding collection time is used as the judgment time. For the subsequent needs of device evaluation, in addition to this target data, the judgment time also needs to correspond to the target data of other intelligent sensors, and it is best that the target data of all intelligent sensors exist at the same judgment time.

[0048] Identify the number of target data corresponding to the judgment moment. If the number of target data is equal to the number of intelligent sensors on the device, then this judgment moment does not need to be processed. However, if the number of target data is less than the number of intelligent sensors, it means that the target data of some intelligent sensors is missing at this judgment moment. Therefore, interpolation processing needs to be performed on the target data of these intelligent sensors.

[0049] Take the acquisition moment that needs interpolation processing as the target moment. It is possible to judge which intelligent sensors' target data is missing at this target moment according to the target data collected by the cloud platform, and mark these intelligent sensors as interpolation sensors. Construct a data change curve through the target data corresponding to the interpolation sensors. Substitute the target moment into the data change curve to calculate the target data at the target moment, and associate the calculated target data with the target moment to complete the interpolation processing of this interpolation sensor. Next, complete the processing of other interpolation sensors or other target moments. After interpolation processing, there is target data of other intelligent sensors at the acquisition moment corresponding to any target data in the cloud platform. In subsequent device evaluation and analysis, multi-source data at the same moment can be extracted, saving the time of temporary processing.

[0050] Embodiment 2: The difference from Embodiment 1 lies in the different scheme for determining the target moment.

[0051] To ensure that the target data can be aligned in time, this example is implemented through interpolation processing. Interpolation processing is affected by data fluctuations. The greater the data fluctuations, the worse the interpolation effect. Therefore, when performing interpolation processing, it is preferred to perform interpolation processing on data with smaller fluctuations.

[0052] Analyze the data stability of each intelligent sensor according to the target data received by the cloud platform. When analyzing the target stability, the target data collected during device anomalies should be excluded to avoid affecting the interpolation effect. Data stability mainly judges whether the target data of each intelligent sensor is easily affected by other intelligent sensors or the environment. If it is not easily affected, it is determined that the stability of this intelligent sensor is good.

[0053] The judgment of data stability can be based on the data fluctuation curve. For example, construct a data fluctuation curve from the target data of several intelligent sensors; based on the data fluctuation curve, take the intelligent sensor with the worst stability as the reference sensor.

[0054] Of course, the judgment of data stability can also be realized based on data analysis methods, such as completing stability analysis through descriptive statistical analysis, regression analysis, variance analysis, and machine learning algorithms.

[0055] Please refer to Figure 3 , in some other preferred embodiments, the influence prediction model obtained in Embodiment 1 can also be used for stability evaluation: The cloud platform calculates the change ratio of each target data with the corresponding change by influencing the prediction model, fits the change ratios of each intelligent sensor into a change ratio curve, and analyzes the change ratio curves of each intelligent sensor through data analysis methods to evaluate the data stability.

[0056] Since the change ratio only considers the mutual influence between intelligent sensors (including other preset interference sources) during calculation, evaluating data stability based on the change ratio can screen out which intelligent sensor is less affected by other intelligent sensors and which is more affected. It can avoid the target data being affected by non-intelligent sensors and reducing the accuracy of data stability evaluation.

[0057] The above embodiments are only used to illustrate the technical method of the present application and not to limit it. Although the present application has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical method of the present application can be modified or equivalently replaced without departing from the spirit and scope of the technical method of the present application.

Claims

1. A device operation data acquisition and processing system based on intelligent sensors, characterized in that: Includes the cloud platform and the edge collection layer connected to it; Edge collection layer: used to collect a number of device operation data of the target device through a number of set intelligent sensors; wherein the device operation data refers to data related to the operating status of the target device; and, sequentially taking the plurality of the equipment operation data as basic data, extracting an impact prediction model based on the basic data; correcting the basic data based on the impact prediction model to obtain target data; Cloud platform: used to analyze the mutual influence between the plurality of smart sensors through an artificial intelligence model to obtain the influence prediction model; and It is used to receive a plurality of the target data and perform interpolation processing on the plurality of the target data to achieve alignment of the plurality of the target data.

2. According to the intelligent sensor-based equipment operation data acquisition and processing system of claim 1, it is characterized in that: The mutual influence between several smart sensors is analyzed by an artificial intelligence model, including: Extracting simulation training data; wherein the simulation training data is obtained by simulating the setting mode and operation mode of several of the smart sensors in the device; The artificial intelligence model constructed by simulating training data is marked as an impact prediction model; wherein the artificial prediction model includes a BP neural network model or a RBF neural network model.

3. The device operation data acquisition and processing system based on intelligent sensors according to claim 2 is characterized in that: The acquisition of the simulation training data includes: Determine a number of smart sensors set in the device, and use the smart sensors as target sensors in turn; mark other smart sensors except the target sensors as non-target sensors; The detection data of the target sensor when the detection device is running is marked as target data one; then the detection data of the target sensor when the non-target sensor is operating normally is simulated according to the simulation rule and marked as target data two; A simulation training data is generated by using the change ratio of the target data 2 to the target data 1 and the corresponding simulation rule; wherein the simulation rule is used to indicate whether the non-target sensor is operating.

4. The device operation data acquisition and processing system based on intelligent sensors according to claim 3 is characterized in that: The acquisition of the simulation rules includes: Marking the operating status of the non-target sensor to obtain a marking group; wherein the operating status includes operating and not operating; Each time, a mark is extracted from the mark group of each non-target sensor, and the extracted marks are integrated into a simulation rule. After several extractions, several simulation rules are obtained.

5. The device operation data acquisition and processing system based on intelligent sensors according to claim 4 is characterized in that: Correcting the basic data based on the impact prediction model includes: Extracting the impact prediction model of the smart sensor corresponding to the basic data and the operating status of other smart sensors when the basic data is collected; The operating states of other intelligent sensors are preprocessed and then input into the impact prediction model to obtain a change ratio; and the basic data are corrected based on the change ratio.

6. The equipment operation data acquisition and processing system based on intelligent sensors according to claim 1 or 5, characterized in that: The interpolation processing of the target data comprises: Extracting a number of target data, and determining a target time that needs to be interpolated according to the number of target data; The target data at the target time is obtained through interpolation processing.

7. The device operation data acquisition and processing system based on intelligent sensors according to claim 6 is characterized in that: The step of determining the target time for interpolation processing based on the plurality of target data includes: Taking the collection time corresponding to any of the target data as the judgment time, calculating the number of target data corresponding to the judgment time; Determine whether the number of target data is consistent with the number of smart sensors; if yes, no interpolation processing is required at the determination time; if no, the determination time is used as the target time.

8. The device operation data acquisition and processing system based on intelligent sensors according to claim 6 is characterized in that: The step of determining the target time for interpolation processing based on the plurality of target data includes: Based on the target data, a smart sensor with the worst stability is selected and marked as a reference sensor; and the collection time of the target data corresponding to the reference sensor is used as the judgment time; Calculate the target data quantity corresponding to the judgment time; judge whether the target data quantity is consistent with the number of smart sensors; if yes, no interpolation processing is required at the judgment time; if no, take the judgment time as the target time.

9. The device operation data acquisition and processing system based on intelligent sensors according to claim 8 is characterized in that: Selecting a smart sensor with poor stability based on the target data includes: Constructing a data fluctuation curve from target data of a plurality of the smart sensors; Based on the data fluctuation curve, the smart sensor with the worst stability is used as a reference sensor.

10. The equipment operation data acquisition and processing system based on intelligent sensors according to claim 9 is characterized in that: After determining the target moment, the smart sensor corresponding to the missing data at the target moment is identified; and interpolation processing is performed based on the target data collected by the smart sensor to obtain the target data at the target moment.

Images