Diesel engine pollutant emission early warning method

Abstract

The invention relates to the technical field of pollutant emission early warning, and discloses a diesel engine pollutant emission early warning method, which comprises the following steps of: determining a diesel engine to be early warned, acquiring data information of the diesel engine to be early warned, and constructing a proportion analogue simulation model of the diesel engine to be early warned based on the data information; deploying a plurality of monitoring grids on the proportion analogue simulation model, obtaining future working data of the diesel engine to be pre-warned, and performing analogue simulation on the future working data on the monitoring grids of the proportion analogue simulation model; the analogue simulation value of each monitoring grid is collected, and the predicted pollutant emission amount of the diesel engine to be pre-warned is calculated according to all the analogue simulation values; whether pollutant emission early warning is sent out to the diesel engine to be early warned or not is judged based on the predicted pollutant emission amount, the pollutant emission condition of the diesel engine can be accurately determined, early warning reminding is sent out in real time, and the influence of pollutants on the environment and human health is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of pollutant emission early warning, in particular to a diesel engine pollutant emission early warning method. BACKGROUND

[0002] With the acceleration of industrialization and the increasing traffic in cities, diesel engines, as a kind of efficient and economical power source, are widely used in transportation, engineering machinery, agricultural machinery, power generation and other fields. However, while providing power, the combustion process of diesel engines inevitably produces various pollutants, including nitrogen oxides (NOx), particulate matter (PM), carbon monoxide (CO), unburned hydrocarbons (HC), etc. These emissions have a serious impact on the environment, such as acid rain, smog, greenhouse effect and negative impact on human health.

[0003] In determining the pollutants emitted by diesel engines, two methods are commonly used. The first is the sensor field detection method, which directly measures and monitors the emitted pollutants by installing various sensors in the diesel engine exhaust system, and measures the concentrations of key pollutants such as carbon monoxide, hydrocarbons, nitrogen oxides, particulate matter in real time. However, this method may be affected by the accuracy of the sensors and changes in environmental conditions. The second method is the diesel engine combustion process fitting calculation method, which predicts the emission characteristics under different working conditions based on detailed simulation and calculation of the diesel engine combustion process. This method usually includes specific emission and displacement calculation. Specific emission refers to the amount of pollutants emitted per unit power or per unit work, while displacement calculation refers to the total amount of pollutants emitted during the entire working cycle. However, this method requires accurate combustion models and detailed input parameters, and is complex to calculate and highly dependent on model accuracy. SUMMARY

[0004] The present application provides a diesel engine pollutant emission early warning method to solve the technical problem that the prior art cannot accurately determine the pollutant emission of a diesel engine and cannot issue real-time emission warnings.

[0005] To achieve the above-mentioned purpose, the present application provides a diesel engine pollutant emission early warning method, comprising:

[0006] determining a diesel engine to be warned, obtaining data information of the diesel engine to be warned, and constructing a proportional simulation simulation model of the diesel engine to be warned based on the data information;

[0007] deploying a plurality of monitoring grids on the proportional simulation simulation model, obtaining future working data of the diesel engine to be warned, and simulating the future working data on the monitoring grids of the proportional simulation simulation model, wherein the future working data includes operating state data, vibration signal data, electrical data, and physical state data.

[0008] collecting simulation values of each monitoring grid, and calculating a predicted pollutant emission of the diesel engine to be warned according to all the simulation values;

[0009] judging whether to issue a pollutant emission warning for the diesel engine to be warned based on the predicted pollutant emission.

[0010] Further, when the data information of the diesel engine to be warned is acquired and the proportional simulation simulation model of the diesel engine to be warned is constructed based on the data information, the method comprises:

[0011] The number of neurons of the input layer, the hidden layer and the output layer is determined based on a preset method, and the number of neurons of the input layer, the number of neurons of the hidden layer and the number of neurons of the output layer are in a proportional relationship, wherein the number of neurons of the input layer is determined according to the number of features, the number of neurons of the output layer is determined according to the type of task, and the number of neurons of the hidden layer is determined according to cross-validation;

[0012] According to the proportional relationship, the weights and biases corresponding to the input layer, the hidden layer and the output layer are calculated respectively;

[0013] The training data set is acquired from the historical data repository of the diesel engine to be warned, the neural network is trained based on the training data set until a preset training termination condition is met, and an initial proportional simulation simulation model is obtained;

[0014] The prediction output of the network is calculated through continuous matrix operations and activation function processing, wherein the matrix operations include that the hidden layer receives input from the input layer, the output layer receives input from the hidden layer, and linear transformation is performed through a weight matrix and a bias vector, the activation function processing includes introducing a nonlinear characteristic, the linear output of each neuron is processed through an activation function, the linear transformation of the input layer and the activation function processing are connected in series to obtain a first output, the first output is transmitted to the hidden layer, the linear transformation of the hidden layer and the activation function processing are connected in series to obtain a second output, the second output is transmitted to the output layer, and the linear transformation of the output layer and the activation function processing are connected in series to obtain the final prediction output;

[0015] The difference between the prediction output and the true target value is quantified using a loss function, and it is judged whether the initial proportional simulation simulation model meets the performance requirement;

[0016] If yes, the proportional simulation simulation model is obtained.

[0017] Further, when the plurality of monitoring grids are deployed on the proportional simulation simulation model, the method comprises:

[0018] obtaining model information of the scaled simulation simulation model, wherein the model information comprises a model volume and a model surface area;

[0019] performing initial deployment on the scaled simulation simulation model based on the model information to obtain a primary deployment strategy, wherein the primary deployment strategy comprises: selecting a preliminary deployment position of a monitoring device according to the model volume and the surface area, and dividing a model surface into a plurality of monitoring grids, and deploying a monitoring device in each grid, wherein the number of the monitoring devices is greater than or equal to 1;

[0020] determining a perception reliability and a perception coverage of each monitoring grid;

[0021] calculating a deployment confidence of the primary deployment strategy according to the perception reliability and the perception coverage of each monitoring grid;

[0022] if the deployment confidence is greater than or equal to a preset deployment confidence, determining that the primary deployment strategy does not need to be adjusted;

[0023] if the deployment confidence is less than the preset deployment confidence, adjusting the primary deployment strategy until the obtained deployment confidence is greater than or equal to the preset deployment confidence.

[0024] Further, in the calculation of the deployment confidence of the primary deployment strategy according to the perception reliability and the perception coverage of each monitoring grid, it comprises:

[0025] the deployment confidence of the primary deployment strategy is calculated according to the following formula:

[0026]

[0027] wherein S is the deployment confidence of the primary deployment strategy, n is the number of the monitoring grids, r1 k is the perception reliability corresponding to the kth monitoring grid, Δr1 k is the standard perception reliability corresponding to the kth monitoring grid, r2 k is the perception coverage corresponding to the kth monitoring grid, Δr2 k is the standard perception coverage corresponding to the kth monitoring grid.

[0028] Further, in the obtaining of the future working data of the diesel engine to be warned, the simulation simulation of the future working data on the monitoring grids of the scaled simulation simulation model comprises:

[0029] obtaining an adjustment interval corresponding to the future working data of the scaled simulation simulation model and the diesel engine to be warned;

[0030] simulate the future working data on the proportional simulation analog model according to the simulation times;

[0031] simulate the future working data on a monitoring grid of the proportional simulation analog model according to the simulation times.

[0032] Further, when collecting the simulation analog values of each monitoring grid and calculating the predicted pollutant emission of the diesel engine to be warned according to all the simulation analog values, comprising:

[0033] obtaining a preset simulation analog value, and dividing all the simulation analog values less than the preset simulation analog value into a first simulation analog value set;

[0034] dividing all the simulation analog values greater than or equal to the preset simulation analog value into a second simulation analog value set;

[0035] calculating a first simulation analog average value of the first simulation analog value set and a second simulation analog average value of the second simulation analog value set;

[0036] counting a first simulation analog value number greater than the first simulation analog average value in the first simulation analog value set and a second simulation analog value number greater than the second simulation analog average value in the second simulation analog value set;

[0037] calculating the predicted pollutant emission of the diesel engine to be warned according to the first simulation analog average value, the second simulation analog average value, the first simulation analog value number and the second simulation analog value number.

[0038] Further, when calculating the predicted pollutant emission of the diesel engine to be warned according to the first simulation analog average value, the second simulation analog average value, the first simulation analog value number and the second simulation analog value number, comprising:

[0039]

[0040] wherein Q is the predicted pollutant emission of the diesel engine to be warned, t1 is a first calculation coefficient, w1 is the first simulation analog average value, Y1 is the first simulation analog value number, Y2 is the second simulation analog value number, and w2 is the second simulation analog average value.

[0041] Further, when judging whether to issue a pollutant emission warning to the diesel engine to be warned based on the predicted pollutant emission, comprising:

[0042] acquire a preset predicted pollutant emission amount, and determine whether to issue a pollutant emission warning to the diesel engine to be warned according to a relationship between the predicted pollutant emission amount and the preset predicted pollutant emission amount;

[0043] When the predicted pollutant emission amount is less than the preset predicted pollutant emission amount, it is determined not to issue a pollutant emission warning to the diesel engine to be warned.

[0044] When the predicted pollutant emission amount is greater than or equal to the preset predicted pollutant emission amount, it is determined to issue a pollutant emission warning to the diesel engine to be warned.

[0045] Further, after determining whether to issue a pollutant emission warning to the diesel engine to be warned based on the predicted pollutant emission amount, the method further comprises:

[0046] extracting all simulation simulation values in the second simulation simulation value set and determining a clustering center;

[0047] determining a clustering distance of each simulation simulation value to the clustering center, performing curve fitting on all clustering distances based on a preset method to obtain a clustering distance fitting curve;

[0048] determining a slope of the clustering distance fitting curve, and determining a next warning time of the diesel engine to be warned based on a slope-period mapping table;

[0049] determining a clustering distance that is not fitted, and calculating an average clustering distance of all clustering distances that are not fitted;

[0050] setting a warning period adjustment coefficient of the diesel engine to be warned based on the average clustering distance, and adjusting the next warning time based on the warning period adjustment coefficient to obtain a next target warning time;

[0051] issuing a periodic pollutant emission warning to the diesel engine to be warned based on the next target warning time.

[0052] Compared with the prior art, the method has the following beneficial effects:

[0053] The application discloses a diesel engine pollutant emission early warning method, determines a diesel engine to be warned, acquires data information of the diesel engine to be warned, and constructs a proportional simulation analog model of the diesel engine to be warned based on the data information; a plurality of monitoring grids are deployed on the proportional simulation analog model, future working data of the diesel engine to be warned are acquired, and the future working data are simulated on the monitoring grids of the proportional simulation analog model; simulation analog values of each monitoring grid are collected, and predicted pollutant emissions of the diesel engine to be warned are calculated according to all the simulation analog values; whether the diesel engine to be warned is warned of pollutant emissions is judged based on the predicted pollutant emissions, the pollutant emission situation of the diesel engine can be accurately determined, early warning and reminding can be timely given, and the influence of pollutants on the environment and human health is reduced. BRIEF DESCRIPTION OF DRAWINGS

[0054] Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments with reference made to the accompanying drawings. The drawings are for purposes of illustration only and are not intended to be limiting in any respect. Moreover, the use of the same reference symbols in different drawings indicates similar or identical items.

[0055] Figure 1 A flowchart of a diesel engine pollutant emission early warning method in an embodiment of the application is shown. DETAILED DESCRIPTION

[0056] The specific embodiments of the application will be further described in conjunction with the drawings and examples. The following examples are used to illustrate the application, but are not used to limit the scope of the application.

[0057] In the description of the present application, it should be understood that the terms "center", "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the purpose of facilitating the description of the present application and simplifying the description, and therefore cannot be understood as indicating or implying that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as limiting the present application.

[0058] The terms "first", "second", "third", etc. are only used for description purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the technical features indicated. Therefore, the features defined with "first", "second", etc. can explicitly or implicitly include one or more of the features. In the description of the present application, unless otherwise specified, the meaning of "a plurality of" is two or more.

[0059] In the description of the present application, it should be noted that unless otherwise explicitly specified and limited, the terms "mounting", "connection", "connecting" should be understood in a broad sense, for example, can be fixed connection, can also be detachable connection, or integral connection, can be mechanical connection, can also be electrical connection, can be direct connection, can also be indirect connection through intermediate medium, can be internal communication of two elements. For those skilled in the art, the specific meanings of the above terms in the present application can be understood according to the specific circumstances.

[0060] The following is a description of the preferred embodiments of the present application in conjunction with the accompanying drawings.

[0061] As shown in Figure 1 Embodiments of the present application disclose a diesel engine pollutant emission early warning method, comprising:

[0062] S110: determining a diesel engine to be warned, acquiring data information of the diesel engine to be warned, and constructing a proportional simulation analog model of the diesel engine to be warned based on the data information;

[0063] In some embodiments of the present application, when the data information of the diesel engine to be warned is acquired and the proportional simulation analog model of the diesel engine to be warned is constructed based on the data information, it comprises:

[0064] The number of neurons of the input layer, the hidden layer and the output layer is determined based on a preset method, and the number of neurons of the input layer, the number of neurons of the hidden layer and the number of neurons of the output layer are in a proportional relationship, wherein the number of neurons of the input layer is determined according to the number of features, the number of neurons of the output layer is determined according to the type of task, and the number of neurons of the hidden layer is determined according to cross-validation;

[0065] According to the proportional relationship, the weights and biases corresponding to the input layer, the hidden layer and the output layer are calculated respectively;

[0066] Acquire a training data set from the historical data repository of the diesel engine to be warned, train the neural network based on the training data set until the preset training termination condition is met, and obtain an initial proportional simulation analog model;

[0067] The prediction output of the network is calculated through continuous matrix operation and activation function processing, wherein the matrix operation includes that the hidden layer receives input from the input layer, the output layer receives input from the hidden layer, and linear transformation is performed through a weight matrix and a bias vector, the activation function processing includes that a nonlinear characteristic is introduced, and the linear output of each neuron is processed through an activation function, the linear transformation and the activation function processing of the input layer are connected in series to obtain a first output, the first output is transmitted to the hidden layer, the linear transformation and the activation function processing of the hidden layer are connected in series to obtain a second output, the second output is transmitted to the output layer, and the linear transformation and the activation function processing of the output layer are connected in series to obtain a final prediction output;

[0068] The difference between the prediction output and the real target value is quantified using a loss function to determine whether the initial scaled simulation model meets the performance requirement.

[0069] If yes, the scaled simulation model is obtained.

[0070] In this embodiment, the data information includes operating state parameters, vibration signal parameters, electrical parameters, physical state parameters and the like.

[0071] In this embodiment, the number of neurons of the input layer, the hidden layer and the output layer is determined based on a preset method (such as an experience rule, cross-validation or the like). The number of neurons between layers is ensured to be in a proportional relationship to maintain the consistency of the network structure.

[0072] The number of neurons of the input layer is determined.

[0073] The number of neurons of the input layer is usually determined by the number of features of the data set. If you have nn features, the input layer should have nn neurons.

[0074] The number of neurons of the output layer is determined.

[0075] The number of neurons of the output layer is usually determined by the type of task:

[0076] Binary classification problem: 1 neuron (usually using Sigmoid activation function).

[0077] Multi-classification problem: mm neurons (usually using Softmax activation function).

[0078] Regression problem: 1 neuron (linear activation function or no activation function).

[0079] The number of neurons of the hidden layer is determined.

[0080] The number of neurons of the hidden layer is determined through cross-validation.

[0081] To maintain consistency in the network structure, ensure that the number of neurons between layers is in a proportional relationship. For example, if the input layer has 100 neurons, the first hidden layer has 50 neurons, and the second hidden layer can have 25 neurons, so the number of neurons between each layer is half of the previous layer.

[0082] In this embodiment, according to the proportional relationship, the corresponding weights and biases are calculated for each layer of neurons. These weights and biases will be used for information transmission and processing in the neural network.

[0083] Weight initialization, initialization methods include:

[0084] Random initialization: Use small random numbers (such as standard normal distribution) to initialize weights.

[0085] Xavier initialization: Especially suitable for Sigmoid and tanh activation functions, avoid gradient vanishing or explosion phenomenon by initializing weight matrix to small, uniformly distributed values.

[0086] He initialization: Especially suitable for ReLU and its variants activation function, avoid gradient vanishing or explosion phenomenon by initializing weight matrix to small, uniformly distributed values.

[0087] Bias initialization; bias is usually initialized to zero or a small constant, such as 0.01.

[0088] In this embodiment, the neural network is trained using the training data set. The training process will continuously adjust the weights and biases until the preset training termination condition is met (such as reaching a certain number of iterations, error threshold or validation set performance).

[0089] In this embodiment, after training is completed, the initial proportional simulation model is obtained. This model can be used for prediction and analysis.

[0090] In this embodiment, the network's prediction output is calculated through continuous matrix operations and activation function processing. This step involves the forward propagation of data.

[0091] Linear transformation: Each layer of neurons receives input from the previous layer and performs linear transformation through weight matrix and bias vector.

[0092] Activation function processing: In order to introduce non-linear characteristics, the linear output of each neuron will usually go through an activation function processing. Common activation functions include Sigmoid, ReLU, tanh, etc.

[0093] Layer-by-layer transmission: Linear transformation and activation function processing of each layer are connected in series, starting from the input layer and passing through the output layer to get the final prediction output.

[0094] In this embodiment, a loss function is used to quantify the difference between the prediction output and the true target value. The loss function includes Mean Squared Error (MSE), Cross-Entropy Loss, etc. It can be selected according to the actual situation. The smaller the value of the loss function, the closer the prediction ability of the model to the actual situation. If the value of the loss function is small enough, or the model performs well on other performance indicators, the model is considered to meet the performance requirements. If not satisfied, adjust the network structure or training parameters and retrain the model.

[0095] The beneficial effects of the above technical solutions are: the present application can provide guarantee for the pre-warning of the emission of the diesel engine to be pre-warned by training a proportional simulation simulation model, and accurately realize pre-warning.

[0096] S120: deploying a plurality of monitoring grids on the proportional simulation simulation model, obtaining future working data of the diesel engine to be pre-warned, and simulating the future working data on the monitoring grids of the proportional simulation simulation model, wherein the future working data includes running state data, vibration signal data, electrical data, and physical state data.

[0097] In some embodiments of the present application, when deploying a plurality of monitoring grids on the proportional simulation simulation model, it includes:

[0098] Obtaining model information of the proportional simulation simulation model, wherein the model information includes model volume and model surface area;

[0099] Based on the model information, the initial deployment is carried out on the proportional simulation simulation model to obtain a primary deployment strategy, wherein the primary deployment strategy includes: selecting a preliminary deployment position of a monitoring device according to the model volume and the surface area, and dividing the model surface into a plurality of monitoring grids, each grid deploying a monitoring device, and the number of monitoring devices is greater than or equal to 1;

[0100] Determine the perception reliability and perception coverage of each monitoring grid;

[0101] Calculate the deployment confidence of the primary deployment strategy according to the perception reliability and perception coverage of each monitoring grid;

[0102] If the deployment confidence is greater than or equal to a preset deployment confidence, it is judged that the primary deployment strategy does not need to be adjusted;

[0103] If the deployment confidence is less than the preset deployment confidence, the primary deployment strategy is adjusted until the obtained deployment confidence is greater than or equal to the preset deployment confidence.

[0104] In this embodiment, the preliminary deployment position of the monitoring device is selected according to the model volume and surface area. The model surface is divided into a plurality of monitoring grids, and a monitoring device is deployed in each grid, the number of monitoring devices is greater than or equal to 1, and the type and number of devices to be deployed in each grid are determined, which depends on the monitoring target and the expected monitoring accuracy.

[0105] In this embodiment, the perception reliability of each monitoring grid is analyzed, that is, the probability that the device in the grid can accurately monitor the target. The perception coverage of each monitoring grid is determined, that is, the percentage of the grid covered by the monitoring device.

[0106] In this embodiment, the preset deployment confidence is a threshold as the acceptable minimum deployment confidence.

[0107] The beneficial effects of the above technical solutions are: the present application calculates the deployment confidence of the preliminary deployment strategy according to the perception reliability and perception coverage of each monitoring grid, and adjusts the preliminary deployment strategy according to the deployment confidence and the preset deployment confidence, which aims to achieve the best monitoring effect through continuous evaluation and adjustment, so as to ensure the efficiency and reliability of the monitoring system.

[0108] In some embodiments of the present application, when calculating the deployment confidence of the preliminary deployment strategy according to the perception reliability and perception coverage of each monitoring grid, it includes:

[0109] The deployment confidence of the preliminary deployment strategy is calculated according to the following formula:

[0110]

[0111] Where S is the deployment confidence of the preliminary deployment strategy, n is the number of monitoring grids, r1 k r1 k is the perception reliability corresponding to the kth monitoring grid, Δr1 k r1 k is the standard perception reliability corresponding to the kth monitoring grid, r2 k r2 k is the perception coverage corresponding to the kth monitoring grid, Δr2 k r2 k is the standard perception coverage corresponding to the kth monitoring grid.

[0112] In some embodiments of the present application, when obtaining the future working data of the diesel engine to be warned, simulating the future working data on the monitoring grid of the proportional simulation simulation model, it includes:

[0113] Obtain the adjustment interval of the proportional simulation simulation model and the diesel engine to be warned corresponding to the future working data;

[0114] Set the simulation simulation times of the future working data on the proportional simulation simulation model according to the adjustment interval;

[0115]

[0116] wherein P is the number of simulation times, A(b, c) is the adjustment interval of the proportional simulation model and the diesel engine to be warned corresponding to future working data, A(b, c) e is the right boundary value of the adjustment interval of the proportional simulation model and the diesel engine to be warned corresponding to future working data, A(b, c) f is the left boundary value of the adjustment interval of the proportional simulation model and the diesel engine to be warned corresponding to future working data;

[0117] simulating the future working data on the monitoring grid of the proportional simulation model based on the number of simulation times.

[0118] In this embodiment, the adjustment interval refers to the predicted range of various working condition changes that the diesel engine may encounter in future working processes. These intervals are usually determined by factors such as the working load of the equipment, environmental conditions, etc. The data sources of the adjustment interval include historical operation data, equipment performance parameters, and expected changes in working environment. Through analysis and prediction of historical and real-time data, the future working data adjustment interval can be obtained.

[0119] In this embodiment, for example, the load variation range may be 5%-100%, the temperature variation range may be -20℃ to 40℃, and the speed variation range may be 600rpm to 2400rpm, etc. The above are examples and are not specifically limited.

[0120] The beneficial effects of the above technical solution are: the present application simulates the future working data on the monitoring grid of the proportional simulation model based on the number of simulation times, which can fully evaluate the performance and reliability of the diesel engine. By setting the number of simulation times, the accuracy and coverage of the simulation can be improved. It is helpful to optimize the design and operation strategy of the diesel engine.

[0121] S130: Collecting simulation values of each monitoring grid, calculating the predicted pollutant emissions of the diesel engine to be warned according to all simulation values;

[0122] In some embodiments of the present application, when collecting simulation values of each monitoring grid and calculating the predicted pollutant emissions of the diesel engine to be warned according to all simulation values, it includes:

[0123] Obtaining a preset simulation value, dividing all simulation values less than the preset simulation value into a first simulation value set;

[0124] divide all simulation simulation values greater than or equal to the preset simulation simulation value into a second simulation simulation value set;

[0125] calculate a first simulation simulation average value of the first simulation simulation value set, and calculate a second simulation simulation average value of the second simulation simulation value set;

[0126] count a first simulation simulation value number of the first simulation simulation values greater than the first simulation simulation average value, and count a second simulation simulation value number of the second simulation simulation values greater than the second simulation simulation average value;

[0127] calculate a predicted pollutant emission amount of the diesel engine to be warned according to the first simulation simulation average value, the second simulation simulation average value, the first simulation simulation value number and the second simulation simulation value number.

[0128] In the embodiment, the preset simulation simulation value is set based on specific simulation requirements and targets, and is used to divide the simulation simulation values. The preset simulation simulation value is preferably 8.

[0129] The above technical solution has the following beneficial effects: the predicted pollutant emission amount of the diesel engine to be warned is calculated according to the first simulation simulation average value, the second simulation simulation average value, the first simulation simulation value number and the second simulation simulation value number, which provides the predicted pollutant emission amount of the diesel engine to be warned, lays a foundation for emission warning, provides warning data, avoids prediction errors, and affects the normal work of the diesel engine.

[0130] In some embodiments of the present application, when the predicted pollutant emission amount of the diesel engine to be warned is calculated according to the first simulation simulation average value, the second simulation simulation average value, the first simulation simulation value number and the second simulation simulation value number, it includes:

[0131]

[0132] wherein Q is the predicted pollutant emission amount of the diesel engine to be warned, t1 is a first calculation coefficient, w1 is the first simulation simulation average value, Y1 is the first simulation simulation value number, Y2 is the second simulation simulation value number, and w2 is the second simulation simulation average value.

[0133] S140: judging whether to issue a pollutant emission warning to the diesel engine to be warned based on the predicted pollutant emission amount.

[0134] In some embodiments of the present application, when it is judged whether to issue a pollutant emission warning to the diesel engine to be warned based on the predicted pollutant emission amount, it includes:

[0135] acquire a preset predicted pollutant emission amount, determine whether to issue a pollutant emission warning to the diesel engine to be warned according to a relationship between the predicted pollutant emission amount and the preset predicted pollutant emission amount;

[0136] when the predicted pollutant emission amount is less than the preset predicted pollutant emission amount, it is determined not to issue a pollutant emission warning to the diesel engine to be warned;

[0137] when the predicted pollutant emission amount is greater than or equal to the preset predicted pollutant emission amount, it is determined to issue a pollutant emission warning to the diesel engine to be warned.

[0138] In this embodiment, the preset predicted pollutant emission amount is a value for measuring whether the emission of pollutants meets relevant requirements, and can be set according to the actual situation of the diesel engine to meet the emission standard, and is preferably 8 g / kwh.

[0139] The above technical solution has the beneficial effects that the emission of pollutants of the diesel engine can be accurately determined, a warning reminder can be issued in real time, and the influence of pollutants on the environment and human health is reduced.

[0140] In some embodiments of the present application, after determining whether to issue a pollutant emission warning to the diesel engine to be warned based on the predicted pollutant emission amount, the method further comprises:

[0141] extracting all simulation simulation values in the second simulation simulation value set and determining a clustering center;

[0142] determining a clustering distance of each simulation simulation value to the clustering center, performing curve fitting on all clustering distances based on a preset method to obtain a clustering distance fitting curve;

[0143] determining a slope of the clustering distance fitting curve, and determining a next warning time of the diesel engine to be warned based on a slope-period mapping table;

[0144] determining a clustering distance that is not fitted, calculating an average clustering distance of all clustering distances that are not fitted;

[0145] setting a warning period adjustment coefficient of the diesel engine to be warned based on the average clustering distance, and adjusting the next warning time based on the warning period adjustment coefficient to obtain a next target warning time;

[0146] periodically issuing a pollutant emission warning to the diesel engine to be warned based on the next target warning time.

[0147] In this embodiment, the preset method includes a least square method, a polynomial fitting method, etc., and can be selected according to requirements.

[0148] In the embodiment, the pre-warning cycle adjustment coefficient of the diesel engine to be pre-warned is set based on the average cluster distance-adjustment coefficient mapping table, and the product value of the adjustment coefficient and the next pre-warning cycle is taken as the next target pre-warning time.

[0149] The beneficial effects of the technical scheme are: the next target pre-warning time is set, the periodic pre-warning of the diesel engine to be pre-warned is realized, and the pre-warning is not timely and unnecessary work is avoided.

[0150] In the description of the above-described embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0151] Although the present application has been described with reference to the embodiments above, various improvements can be made and parts thereof can be replaced with equivalents without departing from the scope of the present application. In particular, each feature in the embodiments disclosed in the present specification can be used in combination with any other feature in any manner, provided that there is no structural conflict. The combinations of these features are not all described in the present specification only for the purpose of omitting the description and saving resources.

[0152] Those skilled in the art can understand that the above are only preferred embodiments of the present application, and are not used to limit the present application. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions recorded in the foregoing embodiments or make equivalent replacements for some technical features. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method of diesel engine pollutant emission early warning, characterized in that, The method comprises the following steps: determining a diesel engine to be warned, obtaining data information of the diesel engine to be warned, and constructing a proportional simulation model of the diesel engine to be warned based on the data information; deploying a plurality of monitoring grids on the proportional simulation model, obtaining future working data of the diesel engine to be warned, and simulating the future working data on the monitoring grids of the proportional simulation model, wherein the future working data comprises running state data, vibration signal data, electrical data, and physical state data; collecting simulation values of each monitoring grid, and calculating a predicted pollutant emission of the diesel engine to be warned based on all the simulation values; judging whether to issue a pollutant emission warning for the diesel engine to be warned based on the predicted pollutant emission.

2. The method of claim 1, wherein, When obtaining the data information of the diesel engine to be warned and constructing the proportional simulation model of the diesel engine to be warned based on the data information, the method comprises the following steps: determining the number of neurons of an input layer, a hidden layer, and an output layer based on a preset method, and the number of neurons of the input layer, the number of neurons of the hidden layer, and the number of neurons of the output layer are in a proportional relationship, wherein the number of neurons of the input layer is determined according to the number of features, the number of neurons of the output layer is determined according to the type of task, and the number of neurons of the hidden layer is determined according to cross-validation; calculating the corresponding weights and biases of the input layer, the hidden layer, and the output layer according to the proportional relationship; obtaining a training data set from a historical data storage of the diesel engine to be warned, training a neural network based on the training data set until a preset training termination condition is met, and obtaining an initial proportional simulation model; calculating the prediction output of the network through continuous matrix operations and activation function processing, wherein the matrix operations comprise that the hidden layer receives input from the input layer, the output layer receives input from the hidden layer, and linear transformation is performed through a weight matrix and a bias vector, the activation function processing comprises introducing a nonlinear characteristic, the linear output of each neuron is processed through an activation function, the linear transformation of the input layer and the activation function processing are connected in series to obtain a first output, the first output is transmitted to the hidden layer, the linear transformation of the hidden layer and the activation function processing are connected in series to obtain a second output, the second output is transmitted to the output layer, and the linear transformation of the output layer and the activation function processing are connected in series to obtain the final prediction output; quantifying the difference between the prediction output and the true target value using a loss function, and judging whether the initial proportional simulation model meets the performance requirement; if yes, the proportional simulation model is obtained.

3. The method of claim 1, wherein the step of determining the amount of diesel engine pollutant emissions comprises the steps of: determining the amount of diesel engine pollutant emissions based on the amount of fuel injected into the engine. When deploying a plurality of monitoring grids on the proportional simulation model, the method comprises the following steps: obtaining model information of the proportional simulation model, wherein the model information comprises a model volume and a model surface area; performing initial deployment on the scale simulation analog model based on the model information, to obtain an initial deployment strategy, wherein the initial deployment strategy comprises: selecting a preliminary deployment position of a monitoring device according to the model volume and the surface area, and dividing a model surface into a plurality of monitoring grids, and deploying a monitoring device in each grid, and the number of the monitoring devices is greater than or equal to 1; determining a perception reliability and a perception coverage of each monitoring grid; calculating a deployment confidence of the initial deployment strategy according to the perception reliability and the perception coverage of each monitoring grid; if the deployment confidence is greater than or equal to a preset deployment confidence, determining that the initial deployment strategy does not need to be adjusted; if the deployment confidence is less than the preset deployment confidence, adjusting the initial deployment strategy until a deployment confidence obtained is greater than or equal to a preset deployment confidence.

4. The method of claim 3, wherein the step of determining the amount of diesel engine exhaust particulate matter comprises: In the calculation of the deployment confidence of the initial deployment strategy according to the perception reliability and the perception coverage of each monitoring grid, the following is included: The deployment confidence of the initial deployment strategy is calculated according to the following formula: where S is the deployment confidence of the primary deployment strategy, n is the number of monitoring grids, r1 k is the sensing reliability corresponding to the kth monitoring grid, Δr1 k is the standard sensing reliability corresponding to the kth monitoring grid, r2 k is the sensing coverage corresponding to the kth monitoring grid, Δr2 k is the standard sensing coverage corresponding to the kth monitoring grid.

5. The method of claim 1, wherein the step of determining the amount of diesel engine pollutant emissions comprises the step of: In the simulation of the future working data of the diesel engine to be warned on the monitoring grid of the scale simulation analog model, the following is included: ​ obtaining an adjustment interval corresponding to the future working data of the scale simulation analog model and the diesel engine to be warned; setting a simulation simulation number of the future working data on the scale simulation analog model according to the adjustment interval; simulating the future working data on the monitoring grid of the scale simulation analog model based on the simulation number.

6. The method of claim 1, wherein the step of determining the amount of diesel engine pollutant emissions comprises the step of: In the acquisition of the simulation simulation value of each monitoring grid and the calculation of the predicted pollutant emission of the diesel engine to be warned according to all the simulation simulation values, the following is included: ​ obtaining a preset simulation simulation value, and dividing all simulation simulation values less than the preset simulation simulation value into a first simulation simulation value set; dividing all simulation simulation values greater than or equal to the preset simulation simulation value into a second simulation simulation value set; calculating a first simulation simulation average value of the first simulation simulation value set and a second simulation simulation average value of the second simulation simulation value set; counting a first simulation simulation value number greater than the first simulation simulation average value in the first simulation simulation value set and a second simulation simulation value number greater than the second simulation simulation average value in the second simulation simulation value set; calculating the predicted pollutant emission of the diesel engine to be warned according to the first simulation simulation average value, the second simulation simulation average value, the first simulation simulation value number and the second simulation simulation value number.

7. The diesel engine pollutant emission early warning method according to claim 6, characterized in that, In the calculation of the predicted pollutant emission of the diesel engine to be warned according to the first simulation simulation average value, the second simulation simulation average value, the first simulation simulation value number and the second simulation simulation value number, the following is included: wherein Q is the predicted pollutant emission of the diesel engine to be warned, t1 is a first calculation coefficient, w1 is the first simulation simulation average value, Y1 is the first simulation simulation value number, Y2 is the second simulation simulation value number, and w2 is the second simulation simulation average value.

8. The method of claim 1, wherein the step of determining the amount of diesel engine pollutant emissions comprises the step of: The method comprises the following steps: ​ acquiring a preset predicted pollutant emission amount, and determining whether to issue a pollutant emission warning to the diesel engine to be warned based on a relationship between the predicted pollutant emission amount and the preset predicted pollutant emission amount; when the predicted pollutant emission amount is less than the preset predicted pollutant emission amount, it is determined that no pollutant emission warning is issued to the diesel engine to be warned; when the predicted pollutant emission amount is greater than or equal to the preset predicted pollutant emission amount, it is determined that a pollutant emission warning is issued to the diesel engine to be warned.

9. The diesel engine pollutant emission early warning method according to claim 6, characterized in that, After determining whether to issue a pollutant emission warning to the diesel engine to be warned based on the predicted pollutant emission amount, the method further comprises the following steps: extracting all simulation simulation values in the second simulation simulation value set and determining a clustering center; determining a clustering distance of each simulation simulation value to the clustering center, performing curve fitting on all clustering distances based on a preset method, and obtaining a clustering distance fitting curve; determining a slope of the clustering distance fitting curve, and determining a next warning time of the diesel engine to be warned based on a slope-period mapping table; determining a clustering distance that is not fitted, calculating an average clustering distance of all clustering distances that are not fitted; based on the average clustering distance, setting a warning period adjustment coefficient of the diesel engine to be warned, and adjusting the next warning time based on the warning period adjustment coefficient to obtain a next target warning time; based on the next target warning time, periodically issuing a pollutant emission warning to the diesel engine to be warned.

Images