CN114577481A - Pollution index monitoring method and device for gas internal combustion engine - Google Patents
Pollution index monitoring method and device for gas internal combustion engine Download PDFInfo
- Publication number
- CN114577481A CN114577481A CN202011403144.3A CN202011403144A CN114577481A CN 114577481 A CN114577481 A CN 114577481A CN 202011403144 A CN202011403144 A CN 202011403144A CN 114577481 A CN114577481 A CN 114577481A
- Authority
- CN
- China
- Prior art keywords
- model
- pollution index
- index monitoring
- internal combustion
- combustion engine
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 246
- 238000002485 combustion reaction Methods 0.000 title claims abstract description 168
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000012549 training Methods 0.000 claims description 22
- 239000007789 gas Substances 0.000 description 152
- MWUXSHHQAYIFBG-UHFFFAOYSA-N nitrogen oxide Inorganic materials O=[N] MWUXSHHQAYIFBG-UHFFFAOYSA-N 0.000 description 12
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 description 10
- 229910002091 carbon monoxide Inorganic materials 0.000 description 7
- 238000010586 diagram Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 239000003546 flue gas Substances 0.000 description 3
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000013145 classification model Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000012806 monitoring device Methods 0.000 description 2
- 239000001301 oxygen Substances 0.000 description 2
- 229910052760 oxygen Inorganic materials 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 239000008186 active pharmaceutical agent Substances 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M15/00—Testing of engines
- G01M15/04—Testing internal-combustion engines
- G01M15/10—Testing internal-combustion engines by monitoring exhaust gases or combustion flame
- G01M15/102—Testing internal-combustion engines by monitoring exhaust gases or combustion flame by monitoring exhaust gases
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M15/00—Testing of engines
- G01M15/04—Testing internal-combustion engines
- G01M15/05—Testing internal-combustion engines by combined monitoring of two or more different engine parameters
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A50/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE in human health protection, e.g. against extreme weather
- Y02A50/20—Air quality improvement or preservation, e.g. vehicle emission control or emission reduction by using catalytic converters
Landscapes
- Chemical & Material Sciences (AREA)
- Engineering & Computer Science (AREA)
- Combustion & Propulsion (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Combined Controls Of Internal Combustion Engines (AREA)
Abstract
The invention discloses a pollution index monitoring method and device of a gas internal combustion engine, a computer readable storage medium and electronic equipment, wherein the method comprises the following steps: sending a pollution index monitoring model request of the gas internal combustion engine to a joint learning server; receiving a pollution index monitoring model sent by the joint learning server; and determining pollution index data of the gas internal combustion engine according to the pollution index monitoring model. According to the technical scheme, a sensor is not required to be installed, the pollution index monitoring model depends on real data, the pollution index monitoring model is not easily influenced by the external environment, and the pollution index data of the gas internal combustion engine can be accurately determined.
Description
Technical Field
The invention relates to the technical field of energy, in particular to a pollution index monitoring method and device of a gas internal combustion engine.
Background
The concentration of carbon monoxide and/or nitrogen oxides in the flue gas discharged by the gas combustion engine is one of the important indicators for judging whether the gas combustion engine operates in an environment-friendly way.
Currently, sensors are commonly used in the industry to measure the concentration of carbon monoxide and/or nitrogen oxides in the exhaust gas of gas-fired internal combustion engines.
However, sensors are susceptible to environmental factors, resulting in large errors in the measured concentrations of carbon monoxide and/or nitrogen oxides.
Disclosure of Invention
The invention provides a pollution index monitoring method and device of a gas internal combustion engine, a computer readable storage medium and electronic equipment, a sensor is not required to be installed, a pollution index monitoring model depends on real data, the pollution index monitoring model is not easily influenced by the external environment, and the pollution index data of the gas internal combustion engine can be more accurately determined.
In a first aspect, the present invention provides a pollution index monitoring method for a gas internal combustion engine, comprising:
sending a pollution index monitoring model request of the gas internal combustion engine to a joint learning server;
receiving a pollution index monitoring model sent by the joint learning server;
and determining pollution index data of the gas internal combustion engine according to the pollution index monitoring model.
In a second aspect, the present invention provides a pollution index monitoring method for a gas internal combustion engine, including:
receiving a pollution index monitoring model request of the gas internal combustion engine sent by an application client;
judging whether a model corresponding to the pollution index monitoring model request exists in a model database;
determining a pollution index monitoring model according to a judgment result of judging whether a model corresponding to the pollution index monitoring model request exists in the model database;
and sending the pollution index monitoring model to the application client so that the application client determines the pollution index data of the gas internal combustion engine according to the pollution index monitoring model.
In a third aspect, the present invention provides an application client, including:
the first sending module is used for sending a pollution index monitoring model request of the gas internal combustion engine to the joint learning server side;
the first receiving module is used for receiving the pollution index monitoring model sent by the joint learning server side;
and the application module is used for determining the pollution index data of the gas internal combustion engine according to the pollution index monitoring model.
In a fourth aspect, the present invention provides a joint learning server, including:
the second receiving module is used for receiving a pollution index monitoring model request of the gas internal combustion engine sent by the application client;
the judging module is used for judging whether a model corresponding to the pollution index monitoring model request exists in a model database;
the model determining module is used for determining a pollution index monitoring model according to a judgment result of judging whether a model corresponding to the pollution index monitoring model request exists in the model database;
and the second sending module is used for sending the pollution index monitoring model to the application client so that the application client can determine the pollution index data of the gas internal combustion engine according to the pollution index monitoring model.
In a fifth aspect, the invention provides a computer-readable storage medium comprising executable instructions which, when executed by a processor of an electronic device, perform the method according to any one of the first or second aspects.
In a sixth aspect, the present invention provides an electronic device, comprising a processor and a memory storing execution instructions, wherein when the processor executes the execution instructions stored in the memory, the processor performs the method according to any one of the first aspect or the second aspect.
The invention provides a pollution index monitoring method and device of a gas internal combustion engine, a computer readable storage medium and electronic equipment. In conclusion, according to the technical scheme of the invention, a sensor is not required to be installed, the pollution index monitoring model depends on real data, the pollution index monitoring model is not easily influenced by the external environment, and the pollution index data of the gas internal combustion engine can be more accurately determined.
Further effects of the above-mentioned unconventional preferred modes will be described below in conjunction with specific embodiments.
Drawings
In order to more clearly illustrate the embodiments or the prior art solutions of the present invention, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments described in the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive labor.
Fig. 1 is a schematic flow chart of a pollution index monitoring method for a gas internal combustion engine according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart illustrating another method for monitoring pollution indicators of a gas combustion engine according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an application client according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a joint learning server according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention;
fig. 6 is a schematic view of a scenario provided in an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be described in detail and completely with reference to the following embodiments and accompanying drawings. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, a pollution index monitoring method for a gas internal combustion engine according to an embodiment of the present invention is provided. The method provided by the embodiment of the invention can be applied to an application client, and particularly can be applied to a server or a general computer. In this embodiment, the method specifically includes the following steps:
Specifically, an application client of the gas internal combustion engine sends a pollution index monitoring model request of the gas internal combustion engine through an API interface, that is, initiates a pollution index monitoring model call. Optionally, the application client is provided on a local server. The application client may be understood as a client for meeting business requirements of the gas internal combustion engine, for example, a client for predicting pollution index data, and fault types of the gas internal combustion engine, and in a scenario of monitoring pollution indexes, the application client does not participate in joint learning, and is only used as a party of model application, in other words, the gas internal combustion engine does not participate in joint learning.
Specifically, the joint learning server is used for performing joint learning with a joint learning client (a client performing joint learning) to obtain a joint learning model, storing the joint learning model, and providing the model for an application client. Moreover, the method can be applied to the interactive scene of at least one application client and one joint learning server, or can also be applied to the scene of at least one application client and a plurality of joint learning servers, namely, the model database to be called is arranged on each joint learning server, and any joint learning server can provide service for the application client to realize the calling of the model in the model database. It can also be understood that, in the above two scenarios, each joint learning server may be provided with a model database and a control layer. The model database stores at least one joint learning model, and the control layer can realize the calling of the model in the model database based on the request of the model calling of the application client.
And 102, receiving a pollution index monitoring model sent by the joint learning server.
The pollution index monitoring model is used for predicting the pollution index data of the gas internal combustion engine.
And 103, determining pollution index data of the gas internal combustion engine according to the pollution index monitoring model.
Specifically, the pollution index data includes the concentration of nitrogen oxides and/or carbon monoxide.
In some feasible implementation modes, a plurality of pollution index monitoring models are provided, the plurality of pollution index monitoring models are screened based on service information of the pollution index monitoring models to determine a target pollution index monitoring model, and the pollution index data of the gas internal combustion engine is predicted based on the target pollution index monitoring model and the operation data of the gas internal combustion engine. It should be understood that the business information indicates the application of the model, and the reference value of the predicted pollution index data of the gas internal combustion engine is ensured based on the actual application of the model. Specifically, step 103 includes:
and receiving the service information of the pollution index monitoring model sent by the joint learning server.
Determining a target pollution index monitoring model from each pollution index monitoring model according to the respective service information of each pollution index monitoring model;
and determining pollution index data of the gas internal combustion engine according to the target pollution index monitoring model and the operation data of the gas internal combustion engine.
It is understood that the business information refers to the related information generated by applying the pollution index monitoring model and the related information of the pollution index monitoring model itself. Specifically, the service information includes the number of model downloads, a model download user, a model training data source, a model training data volume, model accuracy, model generation time, and the number of model updates. The model precision is determined based on feedback data uploaded by an application client using the model, and the feedback data comprises a predicted value and an actual value. It should be noted that the service information is only used as an example, in practical applications, the service information may be various, and specifically, a field name corresponding to the service information to be acquired may be preset according to an actual service requirement, and the field name is encapsulated in the request, so that the request carries the field name corresponding to the service information. The operation data of the gas internal combustion engine is data generated in the operation process of the gas internal combustion engine, and includes but is not limited to on-off state, gas flow, gas temperature, gas pressure, air temperature, air flow, water supply temperature, main steam pressure, main steam temperature and main steam flow, and the specific needs are determined by combining with actual conditions.
As a possible situation, a plurality of pollution index monitoring models are automatically screened based on the service information of the pollution index monitoring models, a target pollution index monitoring model is determined, and user experience is improved. Specifically, the target pollution index monitoring model may be determined by:
and acquiring model requirements of the gas internal combustion engine, and selecting each pollution index monitoring model according to the model requirements and the respective service information of each pollution index monitoring model so as to determine a target pollution index monitoring model.
The model requirement refers to a condition that the model should meet, and includes a plurality of model conditions, for example, the model requirement may be a model precision requirement, a model generation time requirement, a model download frequency requirement, a model training data volume requirement, and the like, and the target pollution index monitoring model is a joint learning model meeting the model requirement. In a first example, if only one pollution index monitoring model meets the model requirement, the pollution index monitoring model is determined as a target pollution index monitoring model; in a second example, if two or more pollution index monitoring models meet the model requirements, the pollution index monitoring models are respectively determined as target pollution index monitoring models; in a third example, the respective priorities of different model conditions in the model requirements are set, the model conditions met by the pollution index monitoring model are determined for each pollution index monitoring model, and the score of the pollution index monitoring model is determined according to the priorities of the model conditions met by the pollution index monitoring model; and then, determining the pollution index monitoring model with the largest score as a target pollution index monitoring model.
And as another possible situation, displaying service information of the pollution index monitoring model to interact with a user, selecting a target pollution index monitoring model by the user, determining the target pollution index monitoring model, and meeting the user requirements. Specifically, the target pollution index monitoring model may be determined by:
displaying respective icons of the pollution index monitoring models and respective service information of the pollution index monitoring models, and determining a target pollution index monitoring model from the pollution index monitoring models according to the acquired external trigger information.
Specifically, the application client corresponding to the gas internal combustion engine displays respective icons and respective service information of all pollution index monitoring models, so that a user can know the application condition of the models and the condition of the models, then the user clicks the pollution index monitoring models to download, the downloaded pollution index monitoring models are determined to be target pollution index monitoring models, interaction is carried out with the user, and the reference value of the target pollution index monitoring models is ensured.
In the above embodiment, when there are a plurality of target pollution index monitoring models, the pollution index data of the gas internal combustion engine predicted by each target pollution index monitoring model is averaged to obtain the pollution index data of the gas internal combustion engine.
Referring to fig. 6, assuming that the carbon monoxide concentration of the gas engine C1 in the energy station C is to be predicted, the monitoring client Cc in the local operation and maintenance server sends a pollution index monitoring model request, then the monitoring client Cc receives a pollution index monitoring model sent by the joint learning server S, predicts the carbon monoxide concentration of the gas engine C1 according to the pollution index monitoring model, and uploads the prediction result to the joint learning server S, if a true value exists, the true value is uploaded to the joint learning server S.
According to the technical scheme, the beneficial effects of the embodiment are as follows: the pollution index monitoring model is called from the joint learning server side through the pollution index monitoring model request, so that the pollution index monitoring model is determined quickly, and the efficiency of obtaining the model is improved; and model selection is carried out through the service information of the pollution index monitoring model, so that the reference value of the predicted oxygen content of the flue gas is ensured.
Fig. 2 shows another pollution index monitoring method for a gas internal combustion engine according to an embodiment of the present invention. The method provided by the embodiment of the invention can be applied to a joint learning server, and particularly can be applied to a server or a general computer. In this embodiment, the method specifically includes the following steps:
The above description of step 101 is not repeated here.
Before model calling is carried out, whether a model corresponding to a pollution index monitoring model request exists in a model database needs to be determined, and model calling can be realized only if the model exists.
In some possible implementation manners, the model database includes models to be called and respective model information of each model to be called; specifically, step 202 includes:
and judging whether the models corresponding to the models to be called and the pollution index monitoring model requests are matched or not according to the model information of the models to be called aiming at each model to be called.
The model database is used for storing the model to be called and the model information of the model to be called, and specifically, the model to be called is a joint learning model. The model information is used to describe information of the model to be called, and may be information such as a model use, a model name, a model download frequency, a model download user, a model training data source, a model training data amount, a model precision, a model generation time, and a model update frequency.
Specifically, whether the model to be called is the model corresponding to the pollution index monitoring model request is judged according to the model information of the model to be called, and in practical application, when the name of the pollution index monitoring model exists in the model information, or words which have the same meaning as the name of the pollution index monitoring model but express different words, the model to be called corresponding to the model information is the model corresponding to the pollution index monitoring model request. At this time, the model corresponding to the pollution index monitoring model request is extracted from the model database, and model calling is completed.
And 203, determining a pollution index monitoring model according to a judgment result of judging whether the model corresponding to the pollution index monitoring model request exists in the model database.
In some possible implementation manners, the determination result includes that a model corresponding to the pollution index monitoring model request exists in the model database; step 103, comprising:
and determining a model corresponding to the pollution index monitoring model request from the model database, and determining the model corresponding to the pollution index monitoring model request as a pollution index monitoring model.
In some possible implementation manners, if a model corresponding to the pollution index monitoring model request exists in the model database, the method further includes:
determining the service information of the pollution index monitoring model from the model database;
and sending the service information of the pollution index monitoring model to the application client.
By sending the respective service information of the pollution index monitoring model to the application client, the user can know the condition of the model, the user can conveniently select the model, and the accuracy of the predicted pollution index data is ensured.
In some possible implementation manners, the determination result includes that no model corresponding to the pollution index monitoring model request exists in the model database; step 103, comprising:
selecting a combined gas internal combustion engine, wherein the combined gas internal combustion engine passes through a combined learning invitation, and the similarity between the combined gas internal combustion engine and the gas internal combustion engine is not less than a preset threshold value;
performing joint learning according to the respective model training data sets of the joint gas internal combustion engines to obtain local pollution index monitoring models;
determining a combined pollution index monitoring model according to each local pollution index monitoring model;
and determining the combined pollution index monitoring model as a pollution index monitoring model.
Each energy station is used as a node in the Internet of things and is provided with a client, if data in the energy station is used for joint learning, the energy station is called a joint energy station, a gas internal combustion engine in the energy station is called a joint gas internal combustion engine, and the client corresponding to the energy station is called a joint learning client. The joint learning ensures that the private data of the user is protected to the maximum extent through a distributed training and encryption technology so as to improve the trust of the user on the artificial intelligence technology. In the embodiment of the application, under a joint learning mechanism, all participants (joint learning clients corresponding to the joint gas internal combustion engines) contribute the encrypted data model to a union, and a joint model is jointly trained. And uploading the gas internal combustion engine operation data of the combined gas internal combustion engine to a corresponding combined learning client, and storing the gas internal combustion engine operation data by the combined learning client.
In this embodiment, when a model corresponding to the pollution index monitoring model request does not exist in the model database, a model needs to be constructed at this time. Determining a combined gas internal combustion engine similar to the gas internal combustion engine in the energy station; and then, performing joint learning based on respective model training data sets of all the joint gas internal combustion engines to obtain a local pollution index monitoring model, wherein the model training data sets comprise gas internal combustion engine operation data of the joint gas internal combustion engines, and specifically, the gas internal combustion engine operation data comprise on-off states, gas flow, gas temperature, gas pressure, air temperature, air flow, water supply temperature, main steam pressure, main steam temperature, main steam flow and historical flue gas oxygen content (labels). And then, determining a combined pollution index monitoring model based on each local pollution index monitoring model, and determining the combined pollution index monitoring model as a pollution index monitoring model. The local pollution index monitoring model refers to a model obtained by model training based on a model training data set of the combined gas internal combustion engine, or a model obtained by model training based on model training data sets of a plurality of combined gas internal combustion engines in a combined learning client.
The combined gas internal combustion engine can be determined by the following 2 implementation modes:
in the implementation mode 1, the joint gas internal combustion engine is determined based on the description information of the candidate gas internal combustion engine which can participate in the joint learning and the description information of the gas internal combustion engine, and the joint gas internal combustion engine and the gas internal combustion engine are similar. Specifically, the combined gas internal combustion engine can be determined by:
acquiring the description information of the gas internal combustion engine and the description information of each candidate gas internal combustion engine, which are requested to be carried by the pollution index monitoring model;
for each candidate gas internal combustion engine, determining the similarity between the gas internal combustion engine and the candidate gas internal combustion engine according to the description information of the gas internal combustion engine and the description information of the candidate gas internal combustion engine;
and determining the combined gas internal combustion engine according to the similarity between each candidate gas internal combustion engine and the gas internal combustion engine.
The pollution index monitoring model requests to carry description information of the gas internal combustion engine, then obtains the description information of the candidate gas internal combustion engine capable of performing joint learning, calculates the similarity between the description information of the gas internal combustion engine and the description information of the candidate gas internal combustion engine to determine the similarity between the candidate gas internal combustion engine and the gas internal combustion engine, and determines the candidate gas internal combustion engine corresponding to the similarity not smaller than a preset threshold value as the joint gas internal combustion engine. Wherein the description information comprises a plurality of parameters and a parameter value of each parameter. The parameters include, but are not limited to, rated capacity, rated efficiency, operation mode, model (indicating the performance, specification and size of the gas combustion engine), brand and operation place, and the specific needs are determined by combining actual conditions. It can be understood that the higher the similarity between the description information of the gas internal combustion engine and the description information of the combined gas internal combustion engine, the higher the reference value of the combined gas internal combustion engine, so as to ensure the accuracy of the subsequently predicted combined gas internal combustion engine. Preferably, the gas combustion engine and the combined gas combustion engine should be of the same type. Alternatively, the similarity of each parameter in the description information of the gas internal combustion engine and the candidate gas internal combustion engine is determined based on the parameter value of each parameter in the description information of the gas internal combustion engine and the candidate gas internal combustion engine, the similarity of the respective parameters is weighted-averaged, and the result is determined as the similarity between the gas internal combustion engine and the candidate gas internal combustion engine. In practical application, the description information of the gas internal combustion engine can be used as model input, the combined gas internal combustion engine is used as model output, a classification model is trained, and the description information of the candidate gas internal combustion engine is input into the trained classification model, so that whether the corresponding energy station is the combined gas internal combustion engine or not is determined.
Implementation 2, the joint gas internal combustion engine is determined based on the joint learning invitation. Specifically, the combined gas internal combustion engine can be determined by:
determining a reference combined gas internal combustion engine according to the similarity between each candidate gas internal combustion engine and the gas internal combustion engine;
respectively sending joint learning invitations to joint learning clients corresponding to the reference joint energy stations;
and respectively determining the reference combined gas internal combustion engines which agree with the joint learning invitation as the combined gas internal combustion engines.
And if the joint learning client feeds back the invitation to pass, the corresponding reference joint gas internal combustion engine is determined as the joint gas internal combustion engine.
Specifically, the joint model can be constructed through 2 implementation modes as follows:
in the implementation mode 1, for each joint learning client, when the difference between a plurality of gas internal combustion engines in a joint energy station corresponding to the joint learning client is large, the joint learning client performs joint learning based on respective model training data sets of the plurality of joint gas internal combustion engines stored in the joint learning client to obtain a local pollution index monitoring model, and when the plurality of gas internal combustion engines in the joint energy station corresponding to the joint learning client are similar, the joint learning client performs joint learning based on respective model training data sets of all the gas internal combustion engines stored in the joint learning client to obtain a local pollution index monitoring model; the local pollution index monitoring models corresponding to the multiple combined learning clients are obtained, the combined pollution index monitoring model is built based on the local pollution index monitoring models corresponding to the multiple combined learning clients, and compared with a local model corresponding to each combined gas internal combustion engine, the calculation amount can be reduced, and the calculation efficiency is improved.
In the implementation mode 2, for each combined gas internal combustion engine, the local pollution index monitoring model is obtained by performing combined learning based on the model training data set of the combined gas internal combustion engine, the local pollution index monitoring models corresponding to the multiple combined gas internal combustion engines are obtained, and the combined model is constructed based on the local pollution index monitoring models corresponding to the multiple combined gas internal combustion engines.
And 204, sending the pollution index monitoring model to the application client so that the application client determines the pollution index data of the gas internal combustion engine according to the pollution index monitoring model.
The pollution index monitoring model may be understood as a model that inputs the operation data of the gas internal combustion engine and outputs the pollution index data, for example, the pollution index monitoring model may be a neural network, a support vector machine, a lifting decision tree, and the like.
Referring to fig. 6, assuming that the carbon monoxide concentration of the gas internal combustion engine C1 in the energy station C is to be predicted, the joint learning server S receives a pollution index monitoring model request sent by the monitoring client Cc, when there is no model corresponding to the pollution index monitoring model request in the model database in the joint learning server S, if the joint gas internal combustion engine is a1, A3, B1, or B2, the joint learning client Ac performs model training based on the operation data of the gas internal combustion engines a1 and A3 in the joint energy station a and uploads model parameters to the joint learning server S, the joint learning client Bc performs model training based on the operation data of the gas internal combustion engines B1 and B2 in the joint energy station B and uploads the model parameters to the joint learning server S, the joint learning server S issues an aggregated model to the joint learning client Ac and the joint learning client Bc for model iteration, the joint learning client Ac and the joint learning client Bc respectively obtain local pollution index monitoring models, and the local pollution index monitoring models obtained by the joint learning client Ac and the joint learning client Bc are fused to obtain a joint pollution index monitoring model. Here, the joint learning client Ac is deployed on the local operating server As, the joint learning client Bc is deployed on the local operating server Bs, and the joint learning client Cc is deployed on the local operating server Cs.
According to the technical scheme, the beneficial effects of the embodiment are as follows: different model acquisition strategies are determined according to the relation between the pollution index monitoring model request and the model database, the pollution index monitoring model is acquired based on the model acquisition strategies, a sensor does not need to be installed, the acquired pollution index monitoring model is not easily influenced by the external environment, and the pollution index data of the gas internal combustion engine can be accurately measured.
Based on the same concept as the method embodiment of the present invention, referring to fig. 3, an embodiment of the present invention further provides an application client, including:
the first sending module 301 is used for sending a pollution index monitoring model request of the gas internal combustion engine to the joint learning server;
a first receiving module 302, configured to receive a pollution index monitoring model sent by the joint learning server;
and the application module 303 is configured to determine pollution index data of the gas internal combustion engine according to the pollution index monitoring model.
In an embodiment of the present invention, the application module 303 includes: a receiving unit, a selecting unit and an application unit; wherein, the first and the second end of the pipe are connected with each other,
the receiving unit is used for receiving the service information of the pollution index monitoring model sent by the joint learning server;
the selection unit is used for determining a target pollution index monitoring model from each pollution index monitoring model according to the respective service information of each pollution index monitoring model;
and the application unit is used for determining pollution index data of the gas internal combustion engine according to the target pollution index monitoring model and the operation data of the gas internal combustion engine.
In an embodiment of the present invention, the selecting unit is configured to obtain a model requirement of the gas internal combustion engine, and select each pollution index monitoring model according to the model requirement and service information of each pollution index monitoring model, so as to determine a target pollution index monitoring model.
In an embodiment of the present invention, the selecting unit is configured to display an icon of each pollution index monitoring model and service information of each pollution index monitoring model, and determine a target pollution index monitoring model from each pollution index monitoring model according to acquired external trigger information.
Based on the same concept as the method embodiment of the present invention, referring to fig. 4, an embodiment of the present invention further provides a joint learning server, including:
the second receiving module 401 is configured to receive a pollution index monitoring model request of the gas internal combustion engine sent by the application client;
a judging module 402, configured to judge whether a model corresponding to the pollution indicator monitoring model request exists in a model database;
a model determining module 403, configured to determine a pollution index monitoring model according to a determination result of determining whether a model corresponding to the pollution index monitoring model request exists in the model database;
a second sending module 404, configured to send the pollution index monitoring model to the application client, so that the application client determines pollution index data of the gas internal combustion engine according to the pollution index monitoring model.
In one embodiment of the invention, the model database comprises models to be called and respective model information of each model to be called;
the determining module 402 is configured to determine, for each to-be-called model, whether the to-be-called model and the model corresponding to the pollution index monitoring model request are matched according to the model information of the to-be-called model.
In an embodiment of the present invention, the determination result includes that a model corresponding to the pollution index monitoring model request exists in the model database;
the model determining module 403 is configured to determine, from the model database, a model corresponding to the pollution index monitoring model request, and determine the model corresponding to the pollution index monitoring model request as a pollution index monitoring model.
In one embodiment of the present invention, the method further comprises: the information determining module and the third sending module; wherein the content of the first and second substances,
the information determination module is used for determining the service information of the pollution index monitoring model from the model database;
and the third sending module is used for sending the service information of the pollution index monitoring model to the application client.
In an embodiment of the present invention, the determination result includes that no model corresponding to the pollution index monitoring model request exists in the model database;
the model determining module 403 includes: the device comprises a selection unit, a training unit and a model determining unit; wherein the content of the first and second substances,
the selection unit is used for selecting a combined gas internal combustion engine, the combined gas internal combustion engine passes through a combined learning invitation, and the similarity between the combined gas internal combustion engine and the gas internal combustion engine is not less than a preset threshold value;
the training unit is used for performing joint learning according to the respective model training data sets of the joint gas internal combustion engines to obtain the local pollution index monitoring models;
the model determining unit is used for determining a combined pollution index monitoring model according to each local pollution index monitoring model; and determining the combined pollution index monitoring model as a pollution index monitoring model.
Fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention. On the hardware level, the electronic device includes a processor 501 and a memory 502 storing execution instructions, and optionally includes an internal bus 503 and a network interface 504. The Memory 502 may include a Memory 5021, such as a Random-Access Memory (RAM), and may further include a non-volatile Memory 5022(non-volatile Memory), such as at least 1 disk Memory; the processor 501, the network interface 504, and the memory 502 may be connected to each other by an internal bus 503, and the internal bus 503 may be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like; the internal bus 503 may be divided into an address bus, a data bus, a control bus, etc., and is indicated by only one double-headed arrow in fig. 5 for convenience of illustration, but does not indicate only one bus or one type of bus. Of course, the electronic device may also include hardware required for other services. When the processor 501 executes execution instructions stored by the memory 502, the processor 501 performs a method in any of the embodiments of the present invention and at least is used to perform the method as shown in fig. 1 or fig. 2.
In a possible implementation mode, the processor reads the corresponding execution instruction from the nonvolatile memory into the memory and then runs the corresponding execution instruction, and the corresponding execution instruction can also be obtained from other equipment so as to form a pollution index monitoring device of the gas internal combustion engine on a logic level. The processor executes the execution instructions stored in the memory, so that the pollution index monitoring method of the gas internal combustion engine provided by any embodiment of the invention is realized through the executed execution instructions.
The processor may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or instructions in the form of software. The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components. The various methods, steps and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
Embodiments of the present invention further provide a computer-readable storage medium, which includes an execution instruction, and when a processor of an electronic device executes the execution instruction, the processor executes a method provided in any one of the embodiments of the present invention. The electronic device may specifically be the electronic device shown in fig. 5; the execution instruction is a computer program corresponding to a pollution index monitoring device of the gas internal combustion engine.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects.
All the embodiments in the invention are described in a progressive manner, and the same and similar parts among the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, as for the apparatus embodiment, since it is substantially similar to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The above description is only an example of the present invention, and is not intended to limit the present invention. Various modifications and alterations to this invention will become apparent to those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.
Claims (10)
1. A pollution index monitoring method for a gas internal combustion engine, comprising:
sending a pollution index monitoring model request of the gas internal combustion engine to a joint learning server;
receiving a pollution index monitoring model sent by the joint learning server;
and determining pollution index data of the gas internal combustion engine according to the pollution index monitoring model.
2. The method of claim 1, wherein determining pollution indicator data for the gas combustion engine from the pollution indicator monitoring model comprises:
receiving the service information of the pollution index monitoring model sent by the joint learning server;
determining a target pollution index monitoring model from each pollution index monitoring model according to the respective service information of each pollution index monitoring model;
and determining pollution index data of the gas internal combustion engine according to the target pollution index monitoring model and the operation data of the gas internal combustion engine.
3. The method according to claim 2, wherein the determining a target pollution index monitoring model from each pollution index monitoring model according to the respective service information of each pollution index monitoring model comprises:
acquiring model requirements of the gas internal combustion engine, and selecting each pollution index monitoring model according to the model requirements and respective service information of each pollution index monitoring model to determine a target pollution index monitoring model;
alternatively, the first and second electrodes may be,
displaying respective icons of the pollution index monitoring models and respective service information of the pollution index monitoring models, and determining a target pollution index monitoring model from the pollution index monitoring models according to the acquired external trigger information.
4. A pollution index monitoring method for a gas internal combustion engine, comprising:
receiving a pollution index monitoring model request of the gas internal combustion engine sent by an application client;
judging whether a model corresponding to the pollution index monitoring model request exists in a model database;
determining a pollution index monitoring model according to a judgment result of judging whether a model corresponding to the pollution index monitoring model request exists in the model database;
and sending the pollution index monitoring model to the application client so that the application client determines the pollution index data of the gas internal combustion engine according to the pollution index monitoring model.
5. The method according to claim 4, wherein the model database comprises models to be called and respective model information of each model to be called;
the judging whether the model corresponding to the pollution index monitoring model request exists in the model database comprises the following steps:
and judging whether the models corresponding to the models to be called and the pollution index monitoring model requests are matched or not according to the model information of the models to be called aiming at each model to be called.
6. The method according to claim 4, wherein the judgment result comprises that a model corresponding to the pollution index monitoring model request exists in the model database;
the determining the pollution index monitoring model according to the judgment result of judging whether the model corresponding to the pollution index monitoring model request exists in the model database comprises the following steps:
and determining a model corresponding to the pollution index monitoring model request from the model database, and determining the model corresponding to the pollution index monitoring model request as a pollution index monitoring model.
7. The method of claim 6, further comprising:
determining the service information of the pollution index monitoring model from the model database;
and sending the service information of the pollution index monitoring model to the application client.
8. The method according to claim 4, wherein the determination result includes that the model corresponding to the pollution index monitoring model request does not exist in the model database;
the determining the pollution index monitoring model according to the judgment result of judging whether the model corresponding to the pollution index monitoring model request exists in the model database comprises the following steps:
selecting a combined gas internal combustion engine, wherein the combined gas internal combustion engine passes through a combined learning invitation, and the similarity between the combined gas internal combustion engine and the gas internal combustion engine is not less than a preset threshold value;
performing joint learning according to the respective model training data sets of the joint gas internal combustion engines to obtain local pollution index monitoring models;
and determining a combined pollution index monitoring model according to each local pollution index monitoring model, and determining the combined pollution index monitoring model as a pollution index monitoring model.
9. An application client, comprising:
the first sending module is used for sending a pollution index monitoring model request of the gas internal combustion engine to the joint learning server side;
the first receiving module is used for receiving the pollution index monitoring model sent by the joint learning server side;
and the application module is used for determining the pollution index data of the gas internal combustion engine according to the pollution index monitoring model.
10. A joint learning server, comprising:
the second receiving module is used for receiving a pollution index monitoring model request of the gas internal combustion engine sent by the application client;
the judging module is used for judging whether a model corresponding to the pollution index monitoring model request exists in a model database;
the model determining module is used for determining a pollution index monitoring model according to a judgment result of judging whether a model corresponding to the pollution index monitoring model request exists in the model database;
and the second sending module is used for sending the pollution index monitoring model to the application client so that the application client can determine the pollution index data of the gas internal combustion engine according to the pollution index monitoring model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011403144.3A CN114577481B (en) | 2020-12-02 | 2020-12-02 | Pollution index monitoring method and device for gas internal combustion engine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011403144.3A CN114577481B (en) | 2020-12-02 | 2020-12-02 | Pollution index monitoring method and device for gas internal combustion engine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114577481A true CN114577481A (en) | 2022-06-03 |
| CN114577481B CN114577481B (en) | 2024-01-12 |
Family
ID=81768671
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011403144.3A Active CN114577481B (en) | 2020-12-02 | 2020-12-02 | Pollution index monitoring method and device for gas internal combustion engine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114577481B (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102445518A (en) * | 2010-10-09 | 2012-05-09 | 胡建华 | Internal combustion engine exhaust on-line measurement and diagnosis method and equipment |
| CN103748340A (en) * | 2011-08-19 | 2014-04-23 | 特斯托股份公司 | Method and measuring arrangement for determining specific and/or absolute emissions values for NOx and/or CO2 in internal combustion engine |
| WO2014133819A1 (en) * | 2013-02-26 | 2014-09-04 | Cummins Ip, Inc. | System and method for dual fuel engines |
| WO2018022746A1 (en) * | 2016-07-26 | 2018-02-01 | Econtrols, Llc | Oxygen monitoring for high-demand low-emission egr systems |
| CN108228840A (en) * | 2018-01-05 | 2018-06-29 | 北京盛世博创信息技术有限公司 | Environment monitoring control method, device, terminal and computer readable storage medium |
| CN108630229A (en) * | 2017-03-22 | 2018-10-09 | 发那科株式会社 | Learning model construction device, abnormal detector, abnormality detection system and server |
| US20190012575A1 (en) * | 2017-07-04 | 2019-01-10 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method, apparatus and system for updating deep learning model |
| WO2019127085A1 (en) * | 2017-12-27 | 2019-07-04 | Volkswagen (China) Investment Co., Ltd. | Processing method, processing apparatus, control device and cloud server |
| CN110210624A (en) * | 2018-07-05 | 2019-09-06 | 第四范式（北京）技术有限公司 | Execute method, apparatus, equipment and the storage medium of machine-learning process |
| CN110785642A (en) * | 2017-06-29 | 2020-02-11 | 珀金斯发动机有限公司 | Engine monitoring device |
| CN111272436A (en) * | 2020-02-11 | 2020-06-12 | 上海交通大学 | Gas turbine NOx prediction emission monitoring system and method |
| US20200210867A1 (en) * | 2018-12-27 | 2020-07-02 | Hubspot, Inc. | Multi-client service system platform |
-
2020
- 2020-12-02 CN CN202011403144.3A patent/CN114577481B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102445518A (en) * | 2010-10-09 | 2012-05-09 | 胡建华 | Internal combustion engine exhaust on-line measurement and diagnosis method and equipment |
| CN103748340A (en) * | 2011-08-19 | 2014-04-23 | 特斯托股份公司 | Method and measuring arrangement for determining specific and/or absolute emissions values for NOx and/or CO2 in internal combustion engine |
| WO2014133819A1 (en) * | 2013-02-26 | 2014-09-04 | Cummins Ip, Inc. | System and method for dual fuel engines |
| WO2018022746A1 (en) * | 2016-07-26 | 2018-02-01 | Econtrols, Llc | Oxygen monitoring for high-demand low-emission egr systems |
| CN108630229A (en) * | 2017-03-22 | 2018-10-09 | 发那科株式会社 | Learning model construction device, abnormal detector, abnormality detection system and server |
| CN110785642A (en) * | 2017-06-29 | 2020-02-11 | 珀金斯发动机有限公司 | Engine monitoring device |
| US20190012575A1 (en) * | 2017-07-04 | 2019-01-10 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method, apparatus and system for updating deep learning model |
| WO2019127085A1 (en) * | 2017-12-27 | 2019-07-04 | Volkswagen (China) Investment Co., Ltd. | Processing method, processing apparatus, control device and cloud server |
| CN108228840A (en) * | 2018-01-05 | 2018-06-29 | 北京盛世博创信息技术有限公司 | Environment monitoring control method, device, terminal and computer readable storage medium |
| CN110210624A (en) * | 2018-07-05 | 2019-09-06 | 第四范式（北京）技术有限公司 | Execute method, apparatus, equipment and the storage medium of machine-learning process |
| US20200210867A1 (en) * | 2018-12-27 | 2020-07-02 | Hubspot, Inc. | Multi-client service system platform |
| CN111272436A (en) * | 2020-02-11 | 2020-06-12 | 上海交通大学 | Gas turbine NOx prediction emission monitoring system and method |
Non-Patent Citations (2)
| Title |
|---|
| M. GRABA; A. BIENIEK: "Monitoring system of harmful substances emission at Compression Ignition engine with Exhaust Gas Recirculation", 2013 INTERNATIONAL SYMPOSIUM ON ELECTRODYNAMIC AND MECHATRONIC SYSTEMS (SELM), pages 39 - 40 * |
| 范俊峰;: "物联网下环境污染智能监测系统设计研究", 环境科学与管理, no. 09, pages 126 - 130 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114577481B (en) | 2024-01-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111950225B (en) | Chip layout method and device, storage medium and electronic equipment | |
| CN110287332B (en) | Method and device for selecting simulation model in cloud environment | |
| CN111325417B (en) | Method and device for realizing privacy protection and realizing multi-party collaborative updating of business prediction model | |
| CN107967204B (en) | Method and system for measuring line down pressure and terminal equipment | |
| CN104601438A (en) | Friend recommendation method and device | |
| US11057787B2 (en) | Method and test system for mobile network testing as well as prediction system | |
| CN109167816A (en) | Information-pushing method, device, equipment and storage medium | |
| CN110334816B (en) | Industrial equipment detection method, device, equipment and readable storage medium | |
| CN110569159A (en) | Baffle generation method, device, equipment and computer storage medium | |
| CN113254472A (en) | Parameter configuration method, device, equipment and readable storage medium | |
| CN110929867A (en) | Method, device and storage medium for evaluating and determining neural network structure | |
| CN112861346A (en) | Data processing system, method and electronic equipment | |
| CN111738463A (en) | Operation and maintenance method, device, system, electronic equipment and storage medium | |
| CN112861492A (en) | Method and device for linkage calculation between internal tables of report table and electronic equipment | |
| CN115858311A (en) | Operation and maintenance monitoring method and device, electronic equipment and readable storage medium | |
| CN114577481B (en) | Pollution index monitoring method and device for gas internal combustion engine | |
| CN109102357A (en) | A kind of method for pushing based on Articles detecting, device and terminal | |
| CN111190801A (en) | Recommendation system testing method and device and electronic equipment | |
| CN106648895A (en) | Data processing method and device, and terminal | |
| US20220405610A1 (en) | Distributing structure risk assessment using information distribution stations | |
| CN114593920B (en) | Method and device for measuring oxygen content of exhaust gas of gas combustion engine and readable storage medium | |
| CN114580257A (en) | Method and device for measuring oxygen content in flue gas of gas internal combustion engine and readable storage medium | |
| CN111176965B (en) | Recommendation system pre-release test method and device and electronic equipment | |
| CN109858119B (en) | Dynamic energy efficiency modeling method and device, readable medium and electronic equipment | |
| CN114580258A (en) | Method and device for measuring oxygen content in flue gas of gas internal combustion engine |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20231211 Address after: 2101 Science and Technology Innovation Base, Hangyidao Free Trade Zone, Langfang Airport Economic Zone, Daxing District, Beijing, China (Hebei) Pilot Free Trade Zone, Daxing Airport Area Applicant after: Xinao Xinzhi Technology Co.,Ltd. Address before: 100020 10th floor, Motorola building, 1 Wangjing East Road, Chaoyang District, Beijing Applicant before: ENNEW DIGITAL TECHNOLOGY Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |