Fuel monitoring and sensing method based on AI

Abstract

The invention provides a fuel monitoring and sensing method based on AI, and relates to the technical field of fuel monitoring, and the method comprises the steps: obtaining fuel state data of a target fuel based on a preset sensor, and carrying out the data processing to obtain first state data; a fuel monitoring method capable of being used for fuel monitoring is intelligently obtained based on AI, optimization is carried out, and an optimized monitoring method is obtained; carrying out state monitoring on the target fuel based on an optimized monitoring method to obtain a first monitoring result, and carrying out first prediction on the first monitoring result in combination with a fuel prediction model of the target fuel, so as to carry out first analysis on the first monitoring result and the first prediction result; and displaying and early warning the real-time state of the target fuel based on the first analysis result. The monitoring method capable of being used for fuel monitoring is intelligently obtained through the AI, the fuel monitoring method is optimized in combination with the first state data of the target fuel, and meanwhile comprehensive analysis is conducted in combination with the fuel prediction result, so that monitoring and sensing of the fuel can be more accurate and effective.

Description

Technical Field

[0001] The present invention relates to the field of fuel monitoring technology, and in particular to an AI-based fuel monitoring perception method. Background Art

[0002] At present, with the continuous development of the energy industry, the safe storage and use of fuel has become a key link in ensuring energy supply and preventing safety accidents.

[0003] However, traditional fuel monitoring methods often rely on manual inspections and fixed sensors, which have problems such as blind spots in monitoring and untimely responses.

[0004] In recent years, the rapid development of artificial intelligence (AI) technology has brought new solutions to fuel monitoring. By integrating sensors, cameras, intelligent algorithms and other technologies, it is possible to achieve all-round, all-weather monitoring of fuel facilities, identify abnormal situations in a timely manner and issue early warnings.

[0005] Therefore, the present invention provides an AI-based fuel monitoring perception method. Summary of the invention

[0006] The present invention provides an AI-based fuel monitoring perception method to solve the problems of untimely and inaccurate monitoring response in the prior art.

[0007] The present invention provides an AI-based fuel monitoring perception method, comprising: Step 1: Obtain fuel state data of a target fuel based on a preset sensor, and perform data processing to obtain first state data; Step 2: Obtain a fuel monitoring method that can be used for fuel monitoring based on AI intelligence, and optimize it to obtain an optimized monitoring method; Step 3: Performing state monitoring on the target fuel based on the optimization monitoring method to obtain a first monitoring result, and performing a first prediction on the first monitoring result in combination with the fuel prediction model of the target fuel, thereby performing a first analysis on the first monitoring result and the first prediction result; Step 4: Display and warn the real-time status of the target fuel based on the first analysis result.

[0008] According to the present invention, the fuel state data of the target fuel is obtained based on a preset sensor, and the data is processed to obtain the first state data, including: Step 11: Obtain fuel state data of the target fuel based on a preset sensor, and perform data cleaning and data standardization to obtain initial state data; Step 12: Acquire a state feature related to the fuel state of the target fuel to obtain a first state type; Step 13: extracting state data corresponding to the first state type from the initial state data to obtain first state data.

[0009] According to the present invention, a fuel monitoring method based on AI intelligent acquisition that can be used for fuel monitoring is provided, and optimized to obtain an optimized monitoring method, including: Step 21: intelligently acquiring a first fuel monitoring method that can be used for fuel monitoring based on AI, and obtaining a first fuel monitoring method set; Step 22: Combine the historical state data of the target fuel with the first state data to extract the first fuel monitoring method in the first fuel monitoring method set, thereby obtaining an optimized monitoring method for the target fuel.

[0010] According to the present invention, the historical state data of the target fuel is combined with the first state data to extract the first fuel monitoring method in the first fuel monitoring method set, thereby obtaining the optimized monitoring method of the target fuel, including: Step 221: acquiring a first fuel monitoring method that can be used for fuel monitoring based on AI, obtaining a first fuel monitoring method set, and acquiring a first monitoring data type of each first fuel monitoring method in the first fuel monitoring method set; Step 222: Compare each first monitoring data type with the first state type, thereby determining the type similarity between each first monitoring data type and the first state type, thereby obtaining a first state similarity set; Step 223: sorting each type of similarity in the first state similarity set to obtain a first ordered similarity set; Step 224: Acquire historical state data of the target fuel and historical environmental parameters corresponding to each historical state data, and simultaneously acquire real-time environmental parameters of the target fuel; Step 225: Compare each historical environment parameter with the real-time environment parameter, thereby determining the historical status data corresponding to the historical environment parameter that has the highest degree of consistency with the real-time environment parameter as the first historical status data; Step 226: performing type similarity comparison based on the historical state type corresponding to the first historical state data and the first monitoring data type to obtain a second state similarity set, and sorting based on the type similarity to obtain a second ordered similarity set; Step 227: extracting the first similar monitoring data type with the highest type similarity in the first ordered similarity set, and extracting the second similar monitoring data type with the second highest type similarity in the first ordered similarity set, thereby obtaining the first fuel monitoring method corresponding to the first similar monitoring data type and the second similar monitoring data type, thereby obtaining the second fuel monitoring method set; Step 228: extracting the first similar monitoring data type with the highest type similarity in the second ordered similarity set, and extracting the second similar monitoring data type with the second highest type similarity in the first ordered similarity set, thereby obtaining the first fuel monitoring method corresponding to the first similar monitoring data type and the second similar monitoring data type, thereby obtaining a third fuel monitoring method set; Step 229: Determine whether there is a consistent first fuel monitoring method in the second fuel monitoring method set and the third fuel monitoring method set. If so, use the first fuel monitoring method as the optimized monitoring method for the target fuel.

[0011] According to the optimization monitoring method provided by the present invention, the state of the target fuel is monitored to obtain a first monitoring result, and a fuel prediction model is constructed based on the monitoring perception demand of the target fuel, so as to make a first prediction on the first monitoring result, and a first analysis is performed in combination with the first monitoring result and the first prediction result, including: Step 31: Obtain monitoring sensing requirements of the target fuel, and build a fuel prediction model of the target fuel in combination with fuel parameters of the target fuel; Step 32: Performing state monitoring on the target fuel based on the optimized monitoring method to obtain a first monitoring result; Step 33: Input each historical state data of the target fuel into the optimization monitoring method, thereby obtaining a second state monitoring set; Step 34: Sort the historical moments corresponding to the second state monitoring set to obtain an ordered third state monitoring set, thereby constructing a corresponding state curve, and inputting the state curve into the fuel prediction model to perform state prediction to obtain a state prediction result; Step 35: Integrate each state prediction result to obtain a first prediction result of the target fuel, and combine it with the first monitoring result to obtain a first analysis result of the target fuel.

[0012] According to the present invention, a corresponding state curve is constructed, and the state curve is input into a fuel prediction model to perform state prediction, and a state prediction result is obtained, including: Step 341: classifying the third state monitoring set based on different state types to obtain a third classified state set; Step 342: Obtain a corresponding first state curve based on each third classification state subset in the third classification state set, thereby obtaining a first state curve set; Step 343: Input each first state curve into the fuel prediction model, so as to achieve the state prediction result for each state type.

[0013] According to the present invention, the method for displaying and warning the real-time state of the target fuel based on the first analysis result includes: Step 41: judging the real-time fuel state of the target fuel based on the first analysis result, and determining the first state level of the target fuel based on a preset state-level database; Step 42: extracting a fuel adjustment strategy of a corresponding level based on the first state level, and adjusting the fuel ratio and fuel state of the target fuel based on the fuel adjustment strategy to obtain a first adjustment result; Step 43: Perform a second comparison on the second fuel state corresponding to the first adjustment result and the preset state-level database, and display a warning of the state of the target fuel based on the second comparison result.

[0014] According to the present invention, a second comparison is performed between the second fuel state corresponding to the first adjustment result and the preset state-level database, and a state display warning of the target fuel is performed based on the second comparison result, including: performing a second comparison of a second fuel state of the target fuel corresponding to the first adjustment result with a preset state-level database; If the second state level corresponding to the second fuel state is within the standard state level range, displaying the state of the target fuel based on the second fuel state; If the second state level corresponding to the second fuel state is not within the standard state level range, a state warning of the target fuel is performed based on the second fuel state.

[0015] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention provides an AI-based fuel monitoring perception method, which can be used for fuel monitoring through AI intelligent acquisition of a monitoring method, and optimizes the fuel monitoring method in combination with the first state data of the target fuel, which can make the fuel monitoring method more accurate, and at the same time, conduct a comprehensive analysis in combination with the fuel prediction results, which can make the fuel monitoring perception more accurate and effective. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 It is a flow chart of an AI-based fuel monitoring perception method provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0019] Embodiment 1: The embodiment of the present invention provides a fuel monitoring perception method based on AI, such as Figure 1 As shown, including: Step 1: Obtain fuel state data of a target fuel based on a preset sensor, and perform data processing to obtain first state data; Step 2: Obtain a fuel monitoring method that can be used for fuel monitoring based on AI intelligence, and optimize it to obtain an optimized monitoring method; Step 3: Performing state monitoring on the target fuel based on the optimization monitoring method to obtain a first monitoring result, and performing a first prediction on the first monitoring result in combination with the fuel prediction model of the target fuel, thereby performing a first analysis on the first monitoring result and the first prediction result; Step 4: Display and warn the real-time status of the target fuel based on the first analysis result.

[0020] In this embodiment, the preset sensors include a flow sensor, a pressure sensor, a temperature sensor, a rotation speed sensor, a gas sensor, etc.

[0021] In this embodiment, data processing includes the processes of data standardization, data cleaning and data screening.

[0022] In this embodiment, the first state data refers to state data obtained by processing fuel state data of the target fuel acquired by a preset sensor.

[0023] In this embodiment, the fuel monitoring method refers to a monitoring method that can be used for fuel monitoring. For example, the fuel monitoring method includes physical property monitoring, combustion performance monitoring, emission monitoring, and the like.

[0024] In this embodiment, the optimized monitoring method refers to extracting the corresponding fuel monitoring method based on the historical state data and the first state data, thereby optimizing the method to obtain the monitoring method.

[0025] In this embodiment, the first monitoring result is a monitoring result obtained by monitoring the target fuel based on the optimized monitoring method.

[0026] In this embodiment, the fuel prediction model is a model for predicting the fuel state of the target fuel based on monitoring perception requirements and fuel parameters, wherein the monitoring perception requirements include fuel safety requirements, fuel accuracy requirements, etc., and the fuel parameters include fuel calorific value, sulfur content, density, viscosity and other fuel parameters.

[0027] In this embodiment, the first prediction result refers to a result of predicting the fuel state of the target fuel based on the fuel prediction model.

[0028] In this embodiment, the first analysis refers to a fuel state analysis of the target fuel achieved by integrating the first monitoring result with the first prediction result.

[0029] The beneficial effects of the above technical solution are: by intelligently acquiring a monitoring method that can be used for fuel monitoring through AI, and optimizing the fuel monitoring method in combination with the first state data of the target fuel, the fuel monitoring method can be made more accurate, and at the same time, a comprehensive analysis is performed in combination with the fuel prediction results, which can make the fuel monitoring perception more accurate and effective.

[0030] Embodiment 2: Based on Example 1, the first state data is obtained, including: Step 11: Obtain fuel state data of the target fuel based on a preset sensor, and perform data cleaning and data standardization to obtain initial state data; Step 12: Acquire a state feature related to the fuel state of the target fuel to obtain a first state type; Step 13: extracting state data corresponding to the first state type from the initial state data to obtain first state data.

[0031] In this embodiment, the preset sensors include a flow sensor, a pressure sensor, a temperature sensor, a rotation speed sensor, a gas sensor, etc.

[0032] In this embodiment, data cleaning refers to operations such as cleaning, screening, deduplication, and formatting of data to ensure data quality and accuracy.

[0033] In this embodiment, data normalization is to scale the data so that it falls into a small specific interval, such as (0, 1). This conversion helps to eliminate the influence of different dimensions or magnitudes on data analysis, making the comparison between different features more reasonable. Through normalization, the original data can be converted into dimensionless and magnitude-free standardized values, which facilitates subsequent data analysis and application.

[0034] In this embodiment, the initial state data refers to the fuel state data obtained after data cleaning and data standardization processing is performed on the fuel state data acquired based on the preset sensor.

[0035] In this embodiment, the first state type refers to state characteristics related to the fuel state of the target fuel, wherein the first state type includes temperature, pressure, density, calorific value, flow rate, moisture content, calorific value of combustible mixture, ash melting point, etc.

[0036] In this embodiment, the first state data refers to the state data in the initial state data that matches the first state type.

[0037] The beneficial effect of the above technical solution is that by processing the fuel status data of the target fuel, the obtained first status data can be made more concise, which can improve the fuel monitoring efficiency and reduce data redundancy.

[0038] Embodiment 3: Based on Example 2, a fuel monitoring method that can be used for fuel monitoring is obtained based on AI intelligence and optimized to obtain an optimized monitoring method, including: Step 21: intelligently acquiring a first fuel monitoring method that can be used for fuel monitoring based on AI, and obtaining a first fuel monitoring method set; Step 22: Combine the historical state data of the target fuel with the first state data to extract the first fuel monitoring method in the first fuel monitoring method set, thereby obtaining an optimized monitoring method for the target fuel.

[0039] In this embodiment, the first fuel monitoring method refers to a monitoring method that can be used for fuel monitoring. For example, the first fuel monitoring method includes physical property monitoring, combustion performance monitoring, emission monitoring, and the like.

[0040] In this embodiment, the first fuel monitoring method set refers to a set of monitoring methods that can be used for fuel monitoring.

[0041] In this embodiment, the historical state data refers to the historical fuel state data of the target fuel.

[0042] In this embodiment, optimizing the monitoring method refers to extracting the corresponding fuel monitoring method in the first fuel monitoring method set based on the historical state data and the first state data, thereby optimizing the method to obtain the monitoring method.

[0043] The beneficial effect of the above technical solution is that by optimizing the fuel monitoring method, the obtained fuel monitoring method can be made more accurate, better able to meet the real-time monitoring requirements of the target fuel, and improve the monitoring efficiency.

[0044] Embodiment 4: Based on Example 3, an optimized monitoring method for target fuel is obtained, including: Step 221: acquiring a first fuel monitoring method that can be used for fuel monitoring based on AI, obtaining a first fuel monitoring method set, and acquiring a first monitoring data type of each first fuel monitoring method in the first fuel monitoring method set; Step 222: Compare each first monitoring data type with the first state type, thereby determining the type similarity between each first monitoring data type and the first state type, thereby obtaining a first state similarity set; Step 223: sorting each type of similarity in the first state similarity set to obtain a first ordered similarity set; Step 224: Acquire historical state data of the target fuel and historical environmental parameters corresponding to each historical state data, and simultaneously acquire real-time environmental parameters of the target fuel; Step 225: Compare each historical environment parameter with the real-time environment parameter, thereby determining the historical status data corresponding to the historical environment parameter that has the highest degree of consistency with the real-time environment parameter as the first historical status data; Step 226: performing type similarity comparison based on the historical state type corresponding to the first historical state data and the first monitoring data type to obtain a second state similarity set, and sorting based on the type similarity to obtain a second ordered similarity set; Step 227: extracting the first similar monitoring data type with the highest type similarity in the first ordered similarity set, and extracting the second similar monitoring data type with the second highest type similarity in the first ordered similarity set, thereby obtaining the first fuel monitoring method corresponding to the first similar monitoring data type and the second similar monitoring data type, thereby obtaining the second fuel monitoring method set; Step 228: extracting the first similar monitoring data type with the highest type similarity in the second ordered similarity set, and extracting the second similar monitoring data type with the second highest type similarity in the first ordered similarity set, thereby obtaining the first fuel monitoring method corresponding to the first similar monitoring data type and the second similar monitoring data type, thereby obtaining a third fuel monitoring method set; Step 229: Determine whether there is a consistent first fuel monitoring method in the second fuel monitoring method set and the third fuel monitoring method set. If so, use the first fuel monitoring method as the optimized monitoring method for the target fuel.

[0045] In this embodiment, the first monitoring data type refers to the state data type required to be monitored in the first fuel monitoring method.

[0046] In this embodiment, the first state type refers to a state data type corresponding to the first state data.

[0047] In this embodiment, the type similarity refers to the similarity between the first monitoring data type and each type in the first state type, wherein the value range of the type similarity is [0, 1].

[0048] In this embodiment, the first state similarity set is a set including the similarity of each type corresponding to the first state type.

[0049] In this embodiment, the first ordered similarity set refers to a similarity set obtained by sorting each type of similarity in the first state similarity set according to the size of the type similarity.

[0050] In this embodiment, the real-time environmental parameters include ambient temperature, ambient humidity, pressure, air flow rate, etc.

[0051] In this embodiment, the historical state data refers to the fuel state data corresponding to the target fuel during the historical fuel combustion process.

[0052] In this embodiment, the first historical state data refers to comparing the historical environment parameters corresponding to each historical state data with the real-time environment parameters, thereby extracting the historical state data corresponding to the historical environment parameters with the highest degree of environmental parameter consistency as the first historical state data.

[0053] In this embodiment, the second state similarity set refers to performing type similarity comparison between the historical state type corresponding to the first historical state data and the first monitoring data type.

[0054] In this embodiment, the second ordered similarity set refers to a similarity set obtained by sorting each type of similarity in the second state similarity set according to the size of the type similarity.

[0055] In this embodiment, the second fuel monitoring method set includes the first fuel monitoring method corresponding to the first similar monitoring data type with the highest type similarity in the first ordered similarity set and the first fuel monitoring method corresponding to the first similar monitoring data type with the second highest type similarity in the first ordered similarity set.

[0056] In this embodiment, the third fuel monitoring method set includes the first fuel monitoring method corresponding to the second similar monitoring data type with the highest type similarity in the second ordered similarity set and the first fuel monitoring method corresponding to the second similar monitoring data type with the second highest type similarity in the second ordered similarity set.

[0057] In this embodiment, the optimized monitoring method refers to extracting the first fuel monitoring method that is consistent in the second fuel monitoring method set and the third fuel monitoring method set as the optimized monitoring method.

[0058] The beneficial effect of the above technical solution is that by optimizing the fuel monitoring method, the obtained fuel monitoring method can be made more accurate, better able to meet the real-time monitoring requirements of the target fuel, and improve the monitoring efficiency.

[0059] Embodiment 5: Based on Example 3, a first analysis is performed, including: Step 31: Obtain monitoring sensing requirements of the target fuel, and build a fuel prediction model of the target fuel in combination with fuel parameters of the target fuel; Step 32: Performing state monitoring on the target fuel based on the optimized monitoring method to obtain a first monitoring result; Step 33: Input each historical state data of the target fuel into the optimization monitoring method, thereby obtaining a second state monitoring set; Step 34: Sort the historical moments corresponding to the second state monitoring set to obtain an ordered third state monitoring set, thereby constructing a corresponding state curve, and inputting the state curve into the fuel prediction model to perform state prediction to obtain a state prediction result; Step 35: Integrate each state prediction result to obtain a first prediction result of the target fuel, and combine it with the first monitoring result to obtain a first analysis result of the target fuel.

[0060] In this embodiment, the monitoring perception requirements include fuel safety requirements, fuel accuracy requirements, etc.

[0061] In this embodiment, the fuel parameters include fuel calorific value, sulfur content, density, viscosity and other fuel parameters.

[0062] In this embodiment, the fuel prediction model is a model that predicts the fuel state of the target fuel based on monitoring the perceived demand and fuel parameters.

[0063] In this embodiment, the first monitoring result is a monitoring result obtained by monitoring the target fuel based on the optimized monitoring method.

[0064] In this embodiment, the second state monitoring set refers to a state monitoring result set obtained by inputting the historical state data one by one into the optimization monitoring method to determine the corresponding state monitoring results.

[0065] In this embodiment, the third state monitoring set refers to a monitoring set obtained by sorting the state monitoring results according to the historical moment corresponding to each state monitoring result in the second state monitoring set.

[0066] In this embodiment, the state curve refers to the state curve obtained by inputting the state data in the third state monitoring set into the same coordinate system.

[0067] In this embodiment, the state prediction result is the result of inputting the state curve into the fuel prediction model to predict the fuel state.

[0068] In this embodiment, the first analysis result refers to a fuel state analysis result of the target fuel determined by combining the first monitoring result with each state prediction result.

[0069] The beneficial effect of the above technical solution is that by predicting the state of the target fuel based on the fuel prediction model, the state monitoring of the target fuel can be made more accurate, and fuel state problems can be discovered in time to make state adjustments.

[0070] Embodiment 6: Based on Example 5, a corresponding state curve is constructed, and the state curve is input into the fuel prediction model for state prediction to obtain a state prediction result, including: Step 341: classifying the third state monitoring set based on different state types to obtain a third classified state set; Step 342: Obtain a corresponding first state curve based on each third classification state subset in the third classification state set, thereby obtaining a first state curve set; Step 343: Input each first state curve into the fuel prediction model, so as to achieve the state prediction result for each state type.

[0071] In this embodiment, the third classified state set refers to a set obtained by classifying the third state monitoring set based on different state types, wherein each third classified state subset corresponds to one state type.

[0072] In this embodiment, the first state curve refers to a state curve determined by inputting state data in the third classification state subset into the same coordinate system.

[0073] The beneficial effect of the above technical solution is that by constructing a state curve and thus performing state prediction, the state monitoring of the target fuel can be made more accurate, and fuel state problems can be discovered in time to make state adjustments.

[0074] Embodiment 7: Based on the fifth embodiment, the real-time state of the target fuel is displayed and warned based on the first analysis result, including: Step 41: judging the real-time fuel state of the target fuel based on the first analysis result, and determining the first state level of the target fuel based on a preset state-level database; Step 42: extracting a fuel adjustment strategy of a corresponding level based on the first state level, and adjusting the fuel ratio and fuel state of the target fuel based on the fuel adjustment strategy to obtain a first adjustment result; Step 43: Perform a second comparison on the second fuel state corresponding to the first adjustment result and the preset state-level database, and display a warning of the state of the target fuel based on the second comparison result.

[0075] In this embodiment, the preset state-level database is predetermined based on the fuel parameters of the target fuel.

[0076] In this embodiment, the first state level is a fuel state level corresponding to the real-time fuel state of the target fuel determined according to a preset state-level database.

[0077] In this embodiment, the fuel adjustment strategy refers to a fuel adjustment strategy of a target fuel determined based on the first state level, wherein the fuel adjustment strategy includes adjusting a fuel ratio and adjusting a fuel combustion state.

[0078] In this embodiment, the first adjustment result refers to a fuel result obtained by adjusting the fuel ratio of the target fuel based on the fuel adjustment strategy.

[0079] In this embodiment, the fuel matching includes fuel matching methods such as mixing of different types of fuels, matching of different qualities of the same fuel, matching based on environmental protection and efficiency, and matching based on cost.

[0080] In this embodiment, the second fuel state refers to the fuel state of the target fuel after adjustment.

[0081] In this embodiment, the second comparison refers to comparing the adjusted fuel state with a preset state-level database, thereby determining the state level of the adjusted fuel state.

[0082] In this embodiment, the status display warning means that based on the second comparison result, the second fuel status within the standard status level range is displayed, and the second fuel status not within the standard level range is warned.

[0083] The beneficial effect of the above technical solution is that by adjusting the real-time fuel status of the target fuel, the adjustment result is displayed and warned, so that the fuel monitoring of the target fuel can be made more accurate and effective.

[0084] Embodiment 8: Based on Example 7, a second comparison is performed between the second fuel state corresponding to the first adjustment result and the preset state-level database, and a state display warning of the target fuel is performed based on the second comparison result, including: performing a second comparison of a second fuel state of the target fuel corresponding to the first adjustment result with a preset state-level database; If the second state level corresponding to the second fuel state is within the standard state level range, displaying the state of the target fuel based on the second fuel state; If the second state level corresponding to the second fuel state is not within the standard state level range, a state warning of the target fuel is performed based on the second fuel state.

[0085] In this embodiment, the standard state level range varies according to different fuel types and fuel proportions of the target fuel.

[0086] The beneficial effect of the above technical solution is that by adjusting the real-time fuel status of the target fuel, the adjustment result is displayed and warned, so that the fuel monitoring of the target fuel can be made more accurate and effective.

[0087] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A fuel monitoring perception method based on AI, characterized in that: include: Step 1: Obtain fuel state data of a target fuel based on a preset sensor, and perform data processing to obtain first state data; Step 2: Obtain a fuel monitoring method that can be used for fuel monitoring based on AI intelligence, and optimize it to obtain an optimized monitoring method; Step 3: Performing state monitoring on the target fuel based on the optimization monitoring method to obtain a first monitoring result, and performing a first prediction on the first monitoring result in combination with the fuel prediction model of the target fuel, thereby performing a first analysis on the first monitoring result and the first prediction result; Step 4: Display and warn the real-time status of the target fuel based on the first analysis result.

2. The AI-based fuel monitoring perception method according to claim 1, characterized in that: The fuel state data of the target fuel is acquired based on a preset sensor, and the data is processed to obtain the first state data, including: Step 11: Obtain fuel state data of the target fuel based on a preset sensor, and perform data cleaning and data standardization to obtain initial state data; Step 12: Acquire a state feature related to the fuel state of the target fuel to obtain a first state type; Step 13: extracting state data corresponding to the first state type from the initial state data to obtain first state data.

3. The AI-based fuel monitoring perception method according to claim 2 is characterized in that: Based on AI intelligence, a fuel monitoring method that can be used for fuel monitoring is obtained and optimized to obtain an optimized monitoring method, including: Step 21: intelligently acquiring a first fuel monitoring method that can be used for fuel monitoring based on AI, and obtaining a first fuel monitoring method set; Step 22: Combine the historical state data of the target fuel with the first state data to extract the first fuel monitoring method in the first fuel monitoring method set, thereby obtaining an optimized monitoring method for the target fuel.

4. The AI-based fuel monitoring perception method according to claim 3 is characterized in that: Combining the historical state data of the target fuel with the first state data to extract the first fuel monitoring method in the first fuel monitoring method set, thereby obtaining an optimized monitoring method for the target fuel, including: Step 221: acquiring a first fuel monitoring method that can be used for fuel monitoring based on AI, obtaining a first fuel monitoring method set, and acquiring a first monitoring data type of each first fuel monitoring method in the first fuel monitoring method set; Step 222: Compare each first monitoring data type with the first state type, thereby determining the type similarity between each first monitoring data type and the first state type, thereby obtaining a first state similarity set; Step 223: sorting each type of similarity in the first state similarity set to obtain a first ordered similarity set; Step 224: Acquire historical state data of the target fuel and historical environmental parameters corresponding to each historical state data, and simultaneously acquire real-time environmental parameters of the target fuel; Step 225: Compare each historical environment parameter with the real-time environment parameter, thereby determining the historical status data corresponding to the historical environment parameter that has the highest degree of consistency with the real-time environment parameter as the first historical status data; Step 226: performing type similarity comparison based on the historical state type corresponding to the first historical state data and the first monitoring data type to obtain a second state similarity set, and sorting based on the type similarity to obtain a second ordered similarity set; Step 227: extracting the first similar monitoring data type with the highest type similarity in the first ordered similarity set, and extracting the second similar monitoring data type with the second highest type similarity in the first ordered similarity set, thereby obtaining the first fuel monitoring method corresponding to the first similar monitoring data type and the second similar monitoring data type, thereby obtaining the second fuel monitoring method set; Step 228: extracting the first similar monitoring data type with the highest type similarity in the second ordered similarity set, and extracting the second similar monitoring data type with the second highest type similarity in the first ordered similarity set, thereby obtaining the first fuel monitoring method corresponding to the first similar monitoring data type and the second similar monitoring data type, thereby obtaining a third fuel monitoring method set; Step 229: Determine whether there is a consistent first fuel monitoring method in the second fuel monitoring method set and the third fuel monitoring method set. If so, use the first fuel monitoring method as the optimized monitoring method for the target fuel.

5. The AI-based fuel monitoring perception method according to claim 3 is characterized in that: Based on the optimized monitoring method, the state of the target fuel is monitored to obtain a first monitoring result, and a fuel prediction model is constructed based on the monitoring perception demand of the target fuel, so as to make a first prediction on the first monitoring result, and a first analysis is performed in combination with the first monitoring result and the first prediction result, including: Step 31: Obtain monitoring sensing requirements of the target fuel, and build a fuel prediction model of the target fuel in combination with fuel parameters of the target fuel; Step 32: Performing state monitoring on the target fuel based on the optimized monitoring method to obtain a first monitoring result; Step 33: Input each historical state data of the target fuel into the optimization monitoring method, thereby obtaining a second state monitoring set; Step 34: Sort the historical moments corresponding to the second state monitoring set to obtain an ordered third state monitoring set, thereby constructing a corresponding state curve, and inputting the state curve into the fuel prediction model to perform state prediction to obtain a state prediction result; Step 35: Integrate each state prediction result to obtain a first prediction result of the target fuel, and combine the first monitoring result to obtain a first analysis result of the target fuel.

6. The AI-based fuel monitoring perception method according to claim 5, characterized in that: Construct the corresponding state curve and input the state curve into the fuel prediction model for state prediction to obtain the state prediction results, including: Step 341: classifying the third state monitoring set based on different state types to obtain a third classified state set; Step 342: Obtain a corresponding first state curve based on each third classification state subset in the third classification state set, thereby obtaining a first state curve set; Step 343: Input each first state curve into the fuel prediction model, so as to achieve a state prediction result for each state type.

7. The AI-based fuel monitoring perception method according to claim 5, characterized in that: Based on the first analysis result, a real-time status of the target fuel is displayed and warned, including: Step 41: judging the real-time fuel state of the target fuel based on the first analysis result, and determining the first state level of the target fuel based on a preset state-level database; Step 42: extracting a fuel adjustment strategy of a corresponding level based on the first state level, and adjusting the fuel ratio and fuel state of the target fuel based on the fuel adjustment strategy to obtain a first adjustment result; Step 43: Perform a second comparison on the second fuel state corresponding to the first adjustment result and the preset state-level database, and display an early warning of the state of the target fuel based on the second comparison result.

8. The AI-based fuel monitoring perception method according to claim 7, characterized in that: Performing a second comparison on the second fuel state corresponding to the first adjustment result and the preset state-level database, and performing a state display warning of the target fuel based on the second comparison result, including: performing a second comparison of a second fuel state of the target fuel corresponding to the first adjustment result with a preset state-level database; If the second state level corresponding to the second fuel state is within the standard state level range, displaying the state of the target fuel based on the second fuel state; If the second state level corresponding to the second fuel state is not within the standard state level range, a state warning of the target fuel is performed based on the second fuel state.

Images