Ship and aircraft emission three-dimensional monitoring and data fusion system

Abstract

The invention discloses a ship and aircraft emission three-dimensional monitoring and data fusion system. An emission sensor is used for detecting the detection amount of the ith emission; the flow sensor is used for detecting the flow of instantly discharged fuel and the mass flow of discharged substances; the motion state sensor is used for detecting the instantaneous motion state of the hull or the fuselage; the data fusion unit is respectively connected with the emission sensor, the flow sensor and the motion state sensor, and the data fusion unit is used for executing the following steps: compensating and correcting the detection quantity of the emission to obtain a compensated first detection quantity; obtaining a first prediction value obtained by predicting the instantaneous emission amount of the emissions by using a Kalman filtering model according to the instantaneous motion state detected by the motion state sensor; performing prediction correction on the first detection quantity according to the first prediction value to obtain a second detection quantity; based on the second detection quantity, the detection concentration of the ith emission is obtained, and the accuracy of emission concentration detection under the transient working condition is effectively improved.

Description

Technical Field

[0001] The present disclosure generally relates to the field of pollutant emission monitoring technology, and in particular to a three-dimensional monitoring and data fusion system for ship and aircraft emissions. Background Art

[0002] Pollutant emissions have always been a highly publicized environmental issue. With ships and aircraft being emission sources, effective monitoring of emissions is a pressing issue.

[0003] Related technologies typically achieve higher-precision, higher-frequency sampling through sensor iteration. However, ships and aircraft can experience sudden changes in motion, such as during takeoff or ship acceleration, which can lead to instantaneous changes in pollutant emissions. Despite increasing sampling frequency, existing sensors still struggle to effectively capture pollutants generated during these sudden changes. Summary of the Invention

[0004] In view of the above-mentioned defects or deficiencies in the prior art, it is desired to provide a three-dimensional monitoring and data fusion system for ship and aircraft emissions, which can effectively improve the accuracy of emission concentration detection under transient conditions.

[0005] In a first aspect, embodiments of the present application provide a three-dimensional monitoring and data fusion system for ship and aircraft emissions, the system comprising an emissions sensor, a flow sensor, a motion state sensor, and a data fusion unit; the emissions sensor is configured to detect the amount of an i-th type of emissions, and the emissions sensor corresponds at least one-to-one to each type of emissions; the flow sensor is configured to detect instantaneous fuel flow and emission mass flow; and the motion state sensor is configured to detect the instantaneous motion state of a hull or an aircraft body.

[0006] The data fusion unit is connected to the emission sensor, the flow sensor, and the motion state sensor respectively, and is used to perform the following steps:

[0007] performing compensation correction on the detected amount of the emission to obtain a compensated first detected amount;

[0008] Obtaining a first predicted value obtained by predicting the instantaneous emission amount of the emission according to the instantaneous motion state detected by the motion state sensor using a Kalman filter model;

[0009] Performing a prediction correction on the first detection value according to the first prediction value to obtain a second detection value;

[0010] Based on the second detection amount, the detection concentration of the i-th emission is obtained.

[0011] In some embodiments, the compensation correction includes a mass conservation correction, and performing the compensation correction on the detected amount of the emission to obtain a compensated first detected amount includes:

[0012] Obtaining the instantaneous fuel flow rate detected by the flow sensor, the previously calibrated steady-state emission coefficient and the dynamic correction coefficient;

[0013] determining a mass conservation compensation value according to the fuel flow rate, the steady-state emission coefficient, and the dynamic correction coefficient;

[0014] The detected amount of the emission is compensated and corrected according to the mass conservation compensation value to obtain a compensated first detected amount.

[0015] In some embodiments, the compensation correction includes acceleration correction, and performing the compensation correction on the detected amount of the emission to obtain a compensated first detected amount includes:

[0016] Obtaining the instantaneous acceleration collected by the motion state sensor and the previously calibrated acceleration sensitivity coefficient;

[0017] The detected amount of the emission is compensated and corrected according to the instantaneous acceleration, the acceleration sensitivity coefficient and the reference acceleration to obtain a compensated first detected amount.

[0018] In some embodiments, the compensation correction includes time adaptive correction, and the compensation correction of the detected amount of the emission to obtain a compensated first detected amount includes:

[0019] Obtaining an original time constant corresponding to the emission sensor, an instantaneous acceleration collected by the motion state sensor, and a previously calibrated acceleration threshold;

[0020] determining an adaptive time constant corresponding to the emission sensor according to the original time constant, the instantaneous acceleration, and the acceleration threshold;

[0021] The detected amount of the emission is compensated and corrected according to the adaptive time constant to obtain a compensated first detected amount.

[0022] In some embodiments, obtaining the detected concentration of the i-th emission based on the second detected amount includes:

[0023] Obtain the sensitivity matrix A corresponding to the i-th emission, where the element aji in the sensitivity matrix A is used to represent the response coefficient of the j-th emission sensor to the i-th emission;

[0024] According to preset rules, the second detection quantity is decoupled based on the sensitivity matrix A to obtain the detection concentration of the i-th emission.

[0025] In some embodiments, decoupling the second detection quantity based on the sensitivity matrix A according to a preset rule to obtain the detection concentration of the i-th emission includes:

[0026] When the number of types of the motion state sensors is greater than the number of emissions, the second detection quantity is decoupled based on the sensitivity matrix A using the least squares method to obtain the detection concentration of the i-th emission.

[0027] In some embodiments, decoupling the second detection quantity based on the sensitivity matrix A according to a preset rule to obtain the detection concentration of the i-th emission includes:

[0028] In response to the instantaneous acceleration collected by the motion state sensor, the second detection quantity is decoupled based on the sensitivity matrix A using a recursive least squares method to obtain the detection concentration of the i-th emission.

[0029] In some embodiments, decoupling the second detection quantity based on the sensitivity matrix A according to a preset rule to obtain the detection concentration of the i-th emission includes:

[0030] The second detection quantity is decoupled based on the sensitivity matrix A using the Kalman model to obtain the detection concentration of the i-th emission.

[0031] In some embodiments, obtaining the detected concentration of the i-th emission based on the second detected amount includes:

[0032] The second detection quantity is input into the trained decoupling model to obtain the detection concentration of the i-th emission.

[0033] In some embodiments, the data fusion unit is further configured to perform the following steps:

[0034] The Kalman gain is dynamically adjusted using the first predicted value and the first detected value.

[0035] The present application proposes a three-dimensional monitoring and data fusion system for ship and aircraft emissions. By correcting and compensating the detected emission quantities to obtain a compensated first detected quantity, the system compensates for the sensor's inherent inability to respond to transient dynamic changes, thereby improving the sensor's accuracy in detecting transient changes in the motion state of ships and aircraft. A Kalman filter model is then used to predict the instantaneous emission quantities of the emissions based on the transient motion state detected by the dynamic sensor. The first predicted value is used to perform a predictive correction on the first detected quantity to obtain a second detected quantity, achieving accurate prediction of dynamic operating conditions and providing predictive corrections based on dynamic operating conditions for the sensor's detected quantity. This system enables multi-level correction of three-dimensional monitoring of ship and aircraft emissions and improves the accuracy of the final output detected concentration.

[0036] Additional aspects and advantages of the present invention will be set forth in part in the description which follows and, in part, will be obvious from the description which follows, or may be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Other features, objects and advantages of the present application will become more apparent upon reading the detailed description of non-limiting embodiments made with reference to the following drawings:

[0038] Figure 1 A schematic diagram of the structure of a three-dimensional monitoring and data fusion system for ship and aircraft emissions provided in an embodiment of the present application is shown;

[0039] Figure 2 A schematic diagram showing a flow chart of steps executed by a data fusion unit according to an embodiment of the present application is shown;

[0040] Figure 3 A schematic structural diagram of a computer system suitable for implementing a data fusion unit according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0041] The present application will be further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely for the purpose of explaining the relevant invention and are not intended to limit the invention. It should also be noted that, for ease of description, only portions relevant to the invention are shown in the accompanying drawings.

[0042] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in this application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0043] In order to further illustrate the technical solutions provided by the embodiments of the present application, this is described in detail below with reference to the accompanying drawings and specific embodiments. Although the embodiments of the present application provide the method operation instruction steps shown in the following embodiments or drawings, more or fewer operation instruction steps may be included in the method based on conventional or no creative labor. In the steps where there is no necessary causal relationship logically, the execution order of these steps is not limited to the execution order provided by the embodiments of the present application. The method may be executed in the order of the methods shown in the embodiments or drawings or in parallel during the actual processing process or when the device is executed.

[0044] The specific structural diagram of the three-dimensional monitoring and data fusion system for ship and aircraft emissions in this embodiment is as follows: Figure 1 As shown, it includes: an emission sensor 11, a flow sensor 12, a motion state sensor 13 and a data fusion unit 14.

[0045] The emission sensor 11 is located near the engine exhaust port and is used to detect the amount x of the i-th emission. i , i=1, 2, ..., n, the emission sensors correspond at least one to one with the emission types.

[0046] That is, for each type of emission to be analyzed, an emission sensor with high sensitivity to the emission to be analyzed can be set at the engine exhaust port. In this case, there is a one-to-one correspondence between the emission type and the emission sensor.

[0047] Optionally, in an embodiment of the present application, in order to accurately monitor emissions from ships and aircraft, redundant sensors may be provided for detecting pollutants, such as electrochemical sensors, optical sensors, and semiconductor sensors.

[0048] The flow sensor 12 is installed at the fuel inlet side and the exhaust outlet side of the engine to detect the instantaneous exhaust fuel flow. and emission mass flow

[0049] The motion state sensor 13 is provided on the hull or fuselage for detecting the instantaneous motion state of the hull or fuselage. Optionally, in the embodiment of the present application, the instantaneous motion state is the instantaneous acceleration of the hull or fuselage.

[0050] The data fusion unit 14 is connected to the emission sensor 11 , the flow sensor 12 and the motion state sensor 13 respectively, and is used to receive the collected amounts of the emission sensor 11 , the flow sensor 12 and the motion state sensor 13 , and calculate the corrected detection concentration according to the collected amounts.

[0051] Among them, Figure 2As shown, the data fusion unit 14 is used to perform the following steps:

[0052] Step 201 : Correct and compensate the detected amount of emissions to obtain a compensated first detected amount.

[0053] Step 202 : Obtain a first prediction value by using a Kalman filter model to predict the instantaneous emission amount of the emission according to the instantaneous motion state detected by the motion state sensor.

[0054] Step 203: perform prediction correction on the first detection quantity according to the first prediction value to obtain a second detection quantity.

[0055] Step 204: Based on the second measurement, obtain the detection concentration of the i-th emission.

[0056] It should be noted that the correction and compensation of the detected amount of emissions is a direct compensation correction of the detected amount based on the physical characteristics of the sensor, that is, compensation for the sensor's own lack of ability to respond to instantaneous dynamic changes in a timely manner.

[0057] Therefore, the three-dimensional monitoring and data fusion system for ship and aircraft emissions proposed in the embodiment of the present application corrects and compensates the detected amount of emissions to obtain a compensated first detected amount, thereby compensating for the sensor's own lack of ability to respond to instantaneous dynamic changes, thereby improving the accuracy of the sensor's sensing detection when the motion state of ships and aircraft changes instantaneously. The Kalman filter model is then used to predict the instantaneous emission of emissions based on the instantaneous motion state detected by the dynamic sensor, and the first predicted value is used to predict and correct the first detected amount to obtain a second detected amount, achieving accurate prediction of dynamic working conditions and providing predictive corrections based on dynamic working conditions for the sensor's detected amount, thereby achieving multi-level correction of three-dimensional monitoring of ship and aircraft emissions and improving the accuracy of the final output detection concentration.

[0058] In some embodiments, the compensation correction includes a mass conservation correction. Specifically, performing a compensation correction on the detected amount of emissions to obtain a compensated first detected amount includes: obtaining an instantaneous fuel flow rate detected by a flow sensor, a previously calibrated steady-state emission coefficient, and a dynamic correction coefficient; determining a mass conservation compensation value based on the fuel flow rate, the steady-state emission coefficient, and the dynamic correction coefficient; and performing a compensation correction on the detected amount of emissions based on the mass conservation compensation value to obtain the compensated first detected amount.

[0059] For example, the present application uses the following formula to calculate the mass conservation compensation value:

[0060]

[0061] in, is the mass conservation compensation value, is the fuel flow rate, α is the steady-state emission coefficient, and β is the dynamic correction coefficient.

[0062] Furthermore, after obtaining the mass conservation compensation value, the mass conservation compensation value can be directly added to the first detection quantity, for example, the mass conservation compensation value can be added to the first measurement value, and the sum can be used as the compensated first detection quantity. Alternatively, the weighted sum of the mass conservation compensation value and the first measurement value can be obtained according to a preset weight, and the weighted sum can be used as the compensated first detection quantity.

[0063] It should be noted that in the examples of this application, a steady-state emission coefficient α and a dynamic correction coefficient β were calibrated through simulated acceleration experiments conducted on an experimental platform. The steady-state emission coefficient α is used to establish a basic proportional relationship between fuel flow and emissions, for example, establishing a basic NOx emission relationship of 1.2 ppm per gram of fuel. The dynamic correction coefficient β reflects the hysteresis effect of the transient process and compensates for transient emission deviations caused by the rate of change of fuel flow, for example, capturing additional emissions caused by incomplete combustion during the initial acceleration phase.

[0064] Therefore, the present application jointly corrects the emission detection amount obtained by the sensor through the steady-state emission coefficient α and the dynamic correction coefficient β to solve the sensor measurement deviation caused by combustion lag under transient conditions, especially the sensor measurement deviation caused by combustion lag under acceleration conditions.

[0065] In another feasible embodiment, the compensation correction includes acceleration correction. Specifically, compensating the emission detection amount to obtain a compensated first detection amount includes: obtaining the instantaneous acceleration collected by the motion state sensor and a previously calibrated acceleration sensitivity coefficient; and compensating the emission detection amount based on the instantaneous acceleration, the acceleration sensitivity coefficient, and the reference acceleration to obtain the compensated first detection amount.

[0066] For example, the present application uses the following formula to calculate the acceleration compensation value:

[0067]

[0068] in, is the acceleration compensation value, is the detected amount of emissions, γ is the acceleration sensitivity coefficient, a is the instantaneous acceleration collected by the motion state sensor, and a base is the reference acceleration, a max is the maximum permissible acceleration.

[0069] It should be noted that in the examples of this application, the acceleration sensitivity coefficient γ was calibrated through simulated acceleration experiments conducted on an experimental platform. The acceleration sensitivity coefficient γ is used to compensate for the impact of the mechanical inertia of ships and aircraft on sensor data collection, and to quantify the additional impact of acceleration on emission detection.

[0070] Optionally, before performing acceleration correction, the instantaneous acceleration a and the maximum allowable acceleration a can be determined. max If the instantaneous acceleration a is greater than the maximum allowable acceleration a max , then acceleration correction must be performed if the instantaneous acceleration a is less than or equal to the maximum allowable acceleration a max , you can choose whether to perform acceleration correction.

[0071] In one feasible embodiment, when acceleration correction is necessary, mass conservation correction and acceleration correction can be implemented in stages. Specifically, a mass conservation correction can be first performed on the emission detection quantity to obtain a first detection quantity after first-stage compensation. Then, an acceleration correction can be performed on the first detection quantity after first-stage compensation to obtain a final first detection quantity after compensation.

[0072] Specifically, the instantaneous fuel flow rate detected by the flow sensor is obtained. The previously calibrated steady-state emission coefficient α and dynamic correction coefficient β are calculated based on the fuel flow rate. Steady-state emission coefficient α and dynamic correction coefficient β to determine the mass conservation compensation value Compensation value based on mass conservation The emission detection quantity is corrected for mass conservation, and the first detection quantity after the first stage compensation is obtained. Then, the instantaneous acceleration a collected by the motion state sensor and the previously calibrated acceleration sensitivity coefficient γ are obtained; according to the instantaneous acceleration a, the acceleration sensitivity coefficient γ and the reference acceleration a base , acceleration correction is performed on the detection amount of the emission to obtain the first detection amount after final compensation.

[0073] In another feasible embodiment, the compensation correction may further include time adaptive correction. Compensating the emission detection amount to obtain a compensated first detection amount includes: obtaining an original time constant corresponding to the emission sensor, an instantaneous acceleration collected by the motion state sensor, and a previously calibrated acceleration threshold; determining an adaptive time constant corresponding to the emission sensor based on the original time constant, the instantaneous acceleration, and the acceleration threshold; and compensating the emission detection amount based on the adaptive time constant to obtain the compensated first detection amount.

[0074] Exemplarily, the present application uses the following formula to calculate the first detection amount after time adaptive correction:

[0075]

[0076] Among them, τ corrected is the adaptive time constant corresponding to the emission sensor, τ sensor is the original time constant corresponding to the emission sensor, a is the instantaneous acceleration collected by the motion state sensor, and a crit is the acceleration threshold corresponding to the emission sensor, is the first detection quantity after time adaptive correction, The amount of emissions detected.

[0077] It should be noted that the time constant τ refers to the time required for the sensor output to reach 63.2% of the input value. The smaller τ is, the faster the sensor responds; the larger τ is, the slower the response. In the emission monitoring used in the embodiment of the present application, due to the limitations of physical and chemical processes (such as gas diffusion, chemical reaction time, etc.), the output value of the sensor will lag behind the change in the actual emission concentration. The time constant τ is a parameter that quantifies the degree of this lag. Specifically, the sensor lag effect is offset by adding a compensation term for the rate of change of the sensor output. More specifically, the compensation term coefficient is adaptive to the time constant τ corrected It changes dynamically with acceleration, that is, the greater the acceleration, the smaller τ and the smaller the compensation amount (because the actual hysteresis of the sensor is reduced). Correspondingly, the smaller the acceleration, the larger τ and the larger the compensation amount.

[0078] It should be understood that the acceleration threshold a crit Used to characterize the sensitivity of the emission sensor to acceleration, the maximum allowable acceleration a max and acceleration critical value a crit Can be calibrated separately, for the same emission sensor maximum allowable acceleration a max and acceleration critical value a crit Can be the same or different.

[0079] In a preferred embodiment, the acceleration threshold a crit The acceleration threshold used to characterize the qualitative change of the emission sensor response characteristics. Specifically, in the embodiment of the present application, the acceleration threshold a can be used to characterize the qualitative change of the emission sensor response characteristics. crit Determine different correction intervals, for example, when the instantaneous acceleration a is less than 2 times the acceleration critical value a crit When the instantaneous acceleration a is greater than or equal to 2 times the acceleration critical value a, the above time adaptive correction method can be used for compensation correction. crit When , it means that the adaptive time constant τ corrected If the acceleration cannot change dynamically, a preset time constant is used for compensation correction. The preset time constant is determined by prior calibration.

[0080] Therefore, the embodiments of the present application provide a variety of optional compensation correction schemes for emission sensors, and the multiple compensation correction schemes can be used individually or in combination. Through the compensation correction schemes, the problem of misalignment of emission sensors caused by sudden acceleration changes of ships and aircraft, especially instantaneous acceleration, can be effectively solved. In addition, by prior calibration of the sensor, the matching degree of the compensation correction can be effectively guaranteed, thereby improving the reliability and accuracy of the compensation correction of the emission sensor.

[0081] It should be understood that in the embodiment of the present application, after compensating and correcting the emission detection amount of the emission sensor to obtain the first detection amount, in order to further improve the accuracy of the detection results, the present application further adds dynamic model prediction, that is, uses the Kalman filter model for dynamic prediction.

[0082] Specifically, the Kalman filter model uses the state equation to perform model prediction, predicting the real-time emission detection quantity, that is, the first prediction value, and using the first prediction value to perform prediction correction on the first detection quantity to obtain the second detection quantity.

[0083] It should be understood that in some embodiments, the Kalman filter model can also be used to constrain the results of compensation correction, that is, the detected amount of emissions may be higher than the actual value after multi-dimensional compensation correction. At this time, using the prediction results of the Kalman filter model to perform constraint correction can constrain the multi-dimensional compensation correction and improve the accuracy of the detection amount.

[0084] It should also be noted that the Kalman filter model further utilizes the first detected variable and the first predicted value to dynamically adjust the Kalman gain. In other words, the Kalman filter model can adapt to the dynamic changes of the ship or aircraft. For example, it can dynamically analyze and adjust for abnormal instantaneous acceleration of a ship during a surge, preventing abnormal compensation corrections to the emissions sensor caused by the ship's acceleration due to the surge.

[0085] It should be understood that the Kalman gain is essentially a dynamic weight allocator, enabling intelligent switching between sensor data dominating steady-state conditions and model predictions dominating transient conditions. In other words, the Kalman filter model leverages dynamic predictions and emissions sensor data to leverage the model's forward-looking capabilities in transient conditions while maintaining sensor accuracy in steady-state conditions. This allows for optimal estimation across all operating conditions, providing a theoretically rigorous and engineering-feasible solution for precise emissions monitoring.

[0086] It should also be understood that accurate emissions data is crucial for engine control, emissions monitoring, and environmental compliance. Kalman filtering is a recursive algorithm with relatively low computational complexity, making it suitable for real-time processing in embedded systems. Therefore, it is suitable for use in ship and aircraft systems for data fusion analysis to obtain more accurate detection data, improve system robustness and reliability, and meet the requirements of environmental regulations.

[0087] In some embodiments, due to incomplete combustion, emissions can be composed of multiple substances with different valence states of the same element, or different substances that produce similar reactions to the same sensor. This can cause the emission sensor detection results to contain multiple confusing emissions. For example, an electrochemical NO2 sensor may also respond to SO2, resulting in an artificially high measurement value. Based on this, the present application further proposes a method for determining the detection concentration of the i-th emission based on the detection result (the second detection amount).

[0088] In a feasible embodiment, a sensitivity matrix A corresponding to the i-th emission is obtained, and the element aji of the sensitivity matrix A is used to characterize the response coefficient of the j-th emission sensor to the i-th emission; according to preset rules, the second detection quantity is decoupled based on the sensitivity matrix A to obtain the detection concentration of the i-th emission.

[0089] It should be noted that the sensitivity matrix A is obtained by prior calibration. Specifically, the sensitivity matrix A can be obtained by passing the i-th emission into the j-th emission sensor and recording the sensitivity matrix A of the pure gas x. i The response value y of the jth emission sensor j , then

[0090] In some specific embodiments, the second detection quantity is decoupled based on the sensitivity matrix A according to preset rules to obtain the detection concentration of the i-th emission, including: when the types of motion state sensors are greater than the types of emissions, the least squares method is used to decouple the second detection quantity based on the sensitivity matrix A to obtain the detection concentration of the i-th emission.

[0091] Specifically, in the embodiment of the present application, the least squares method is a weighted least squares method, and the weight matrix used is the inverse noise variance matrix corresponding to the j-th emission sensor.

[0092] In other specific embodiments, the second detection quantity is decoupled based on the sensitivity matrix A according to preset rules to obtain the detection concentration of the i-th emission, including: in response to the instantaneous acceleration collected by the motion state sensor, the second detection quantity is decoupled based on the sensitivity matrix A using recursive least squares method to obtain the detection concentration of the i-th emission.

[0093] It should be noted that the recursive least squares method RLS achieves time-varying parameter tracking by introducing a "forgetting factor". In the ship or aircraft emission detection used in the embodiments of the present application, changes in engine load will cause sudden changes in pollutant concentrations. The recursive least squares method RLS can achieve dynamic parameter tracking through recursive iteration, completing real-time decoupling at a constant computational cost, thereby adapting to instantaneous changes in ships and aircraft.

[0094] Therefore, the present application proposes to adopt different decoupling algorithms under different working conditions, which can not only meet the demand of reducing the amount of calculation under steady-state conditions, but also meet the purpose of improving the decoupling accuracy under transient conditions.

[0095] In some embodiments, according to preset rules, the second detection quantity is decoupled based on the sensitivity matrix A to obtain the detection concentration of the i-th emission, including: using the Kalman model to decouple the second detection quantity based on the sensitivity matrix A to obtain the detection concentration of the i-th emission.

[0096] It can be understood that in the embodiment of the present application, the Kalman model is used in the detection quantity correction and detection concentration decoupling stages respectively, which can reduce the difficulty of deploying the data fusion system and reduce maintenance costs.

[0097] In another feasible embodiment, obtaining the detection concentration of the i-th emission based on the second detection quantity includes: inputting the second detection quantity into a trained decoupling model to obtain the detection concentration of the i-th emission.

[0098] Optionally, the trained decoupling model may be an LSTM model, that is, the LSTM model is trained using historical detection concentrations so that the trained decoupling model can accurately analyze the changing pattern of the detection concentrations.

[0099] Preferably, the historical detection concentrations need to include the detection concentrations of the corresponding emissions before and after the sudden change in the instantaneous motion state of the ship or aircraft, so that the trained decoupling model can fully decouple the accurate detection concentration of the i-th emission based on the change law of the second detection quantity.

[0100] Therefore, the embodiments of the present application propose multiple solutions to the problem of cross-interference in easily confused emission detection, which can adapt to different system deployment environments. In particular, for the transient acceleration mutation conditions of ships or aircraft, a recursive least squares decoupling method with higher adaptability is proposed to improve the robustness of emission detection concentration decoupling.

[0101] It should be noted that although the operations of the present method are described in a particular order in the drawings, this does not require or imply that the operations must be performed in this particular order, or that all illustrated operations must be performed to achieve desirable results.

[0102] Reference below Figure 3 , Figure 3 FIG. 1 shows a schematic diagram of the structure of a computer system suitable for implementing a data fusion unit according to an embodiment of the present application.

[0103] like Figure 3 As shown, the computer system includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage part 308 into the random access memory (RAM) 303. Various programs and data required for the operation instructions of the system are also stored in the RAM 303. The CPU 301, ROM 302 and RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0104] The following components are connected to the I / O interface 305: an input section 306 including a keyboard, a mouse, and the like; an output section 307 including devices such as a cathode ray tube (CRT), a liquid crystal display (LCD), and a speaker; a storage section 308 including devices such as a hard disk; and a communication section 309 including a network interface card such as a LAN card or a modem. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 310 as needed, so that computer programs read therefrom can be installed into the storage section 308 as needed.

[0105] In particular, according to the embodiment of the present application, the above reference flow chart Figure 2 The described process can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 309, and / or installed from a removable medium 311. When the computer program is executed by the central processing unit (CPU) 301, the above-mentioned functions defined in the system of the present application are executed.

[0106] It should be noted that the computer-readable medium shown in this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination of the above. More specific examples of computer-readable storage media can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this application, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, device, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. This propagated data signal can take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transfer a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wire, optical cable, RF, or any suitable combination thereof.

[0107] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operating instructions of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the aforementioned module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than the order marked in the accompanying drawings. For example, the boxes represented by two connections can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operating instruction, or can be implemented using a combination of dedicated hardware and computer instructions.

[0108] The above description is merely a preferred embodiment of the present application and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of disclosure in this application is not limited to the technical solutions formed by a specific combination of the above-mentioned technical features, but also encompasses other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the aforementioned disclosed concepts. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features with similar functions disclosed in this application.

Claims

1. A three-dimensional monitoring and data fusion system for ship and aircraft emissions, characterized by: The system includes an emission sensor, a flow sensor, a motion state sensor, and a data fusion unit; the emission sensor is used to detect the amount of the i-th emission, and the emission sensor has at least one-to-one correspondence with the emission type; the flow sensor is used to detect the instantaneous fuel flow rate and emission mass flow rate; the motion state sensor is used to detect the instantaneous motion state of the hull or fuselage; The data fusion unit is connected to the emission sensor, the flow sensor, and the motion state sensor respectively, and is used to perform the following steps: performing compensation correction on the detected amount of the emission to obtain a compensated first detected amount; Obtaining a first predicted value obtained by predicting the instantaneous emission amount of the emission according to the instantaneous motion state detected by the motion state sensor using a Kalman filter model; Performing a prediction correction on the first detection value according to the first prediction value to obtain a second detection value; Based on the second detection amount, the detection concentration of the i-th emission is obtained.

2. The three-dimensional monitoring and data fusion system for ship and aircraft emissions according to claim 1 is characterized in that: The compensation correction includes mass conservation correction, and the compensation correction is performed on the detection amount of the emission to obtain a compensated first detection amount, including: Obtaining the instantaneous fuel flow rate detected by the flow sensor, the previously calibrated steady-state emission coefficient and the dynamic correction coefficient; determining a mass conservation compensation value according to the fuel flow rate, the steady-state emission coefficient, and the dynamic correction coefficient; The detected amount of the emission is compensated and corrected according to the mass conservation compensation value to obtain a compensated first detected amount.

3. The three-dimensional monitoring and data fusion system for ship and aircraft emissions according to claim 1 is characterized in that: The compensation correction includes acceleration correction, and the compensation correction is performed on the detection amount of the emission to obtain a compensated first detection amount, including: Obtaining the instantaneous acceleration collected by the motion state sensor and the previously calibrated acceleration sensitivity coefficient; The detected amount of the emission is compensated and corrected according to the instantaneous acceleration, the acceleration sensitivity coefficient and the reference acceleration to obtain a compensated first detected amount.

4. The three-dimensional monitoring and data fusion system for ship and aircraft emissions according to claim 1 is characterized in that: The compensation correction includes time adaptive correction, and the compensation correction is performed on the detection amount of the emission to obtain a compensated first detection amount, including: Obtaining an original time constant corresponding to the emission sensor, an instantaneous acceleration collected by the motion state sensor, and a previously calibrated acceleration threshold; determining an adaptive time constant corresponding to the emission sensor according to the original time constant, the instantaneous acceleration, and the acceleration threshold; The detected amount of the emission is compensated and corrected according to the adaptive time constant to obtain a compensated first detected amount.

5. The three-dimensional monitoring and data fusion system for ship and aircraft emissions according to claim 1 is characterized in that: The obtaining of the detection concentration of the i-th emission based on the second detection amount includes: Obtain the sensitivity matrix A corresponding to the i-th emission, where the element aji in the sensitivity matrix A is used to represent the response coefficient of the j-th emission sensor to the i-th emission; According to preset rules, the second detection quantity is decoupled based on the sensitivity matrix A to obtain the detection concentration of the i-th emission.

6. The three-dimensional monitoring and data fusion system for ship and aircraft emissions according to claim 5 is characterized in that: Decoupling the second detection quantity based on the sensitivity matrix A according to a preset rule to obtain the detection concentration of the i-th emission includes: When the number of types of the motion state sensors is greater than the number of emissions, the second detection quantity is decoupled based on the sensitivity matrix A using the least squares method to obtain the detection concentration of the i-th emission.

7. The three-dimensional monitoring and data fusion system for ship and aircraft emissions according to claim 5 is characterized in that: Decoupling the second detection quantity based on the sensitivity matrix A according to a preset rule to obtain the detection concentration of the i-th emission includes: In response to the instantaneous acceleration collected by the motion state sensor, the second detection quantity is decoupled based on the sensitivity matrix A using a recursive least squares method to obtain the detection concentration of the i-th emission.

8. The three-dimensional monitoring and data fusion system for ship and aircraft emissions according to claim 5 is characterized in that: Decoupling the second detection quantity based on the sensitivity matrix A according to a preset rule to obtain the detection concentration of the i-th emission includes: The second detection quantity is decoupled based on the sensitivity matrix A using the Kalman model to obtain the detection concentration of the i-th emission.

9. The three-dimensional monitoring and data fusion system for ship and aircraft emissions according to claim 2 is characterized in that: The obtaining of the detection concentration of the i-th emission based on the second detection amount includes: The second detection quantity is input into the trained decoupling model to obtain the detection concentration of the i-th emission.

10. The three-dimensional monitoring and data fusion system for ship and aircraft emissions according to claim 1 is characterized in that: The data fusion unit is further configured to perform the following steps: The Kalman gain is dynamically adjusted using the first predicted value and the first detected value.

Images