A synchronous monitoring method and system based on industrial waste gas treatment

Abstract

The present invention provides a synchronous monitoring method and system based on industrial waste gas treatment, which relates to the field of digital processing technology. The method includes: through the industrial waste gas treatment intelligent system, the equipment operation index parameter set is retrieved to obtain the equipment state parameter information; the equipment historical operation index parameter set and the equipment historical state parameter information set are obtained to construct an operation index-state parameter model; the equipment sub-state prediction information is obtained; the equipment sub-state detection information is obtained, and the equipment sub-state prediction information is combined for comparison. If the comparison is passed, the synchronous online monitoring topology diagram of industrial waste gas treatment is obtained. The technical problem that the monitoring information of the industrial waste gas treatment device has a certain time delay, resulting in the inability to timely operate and maintain the industrial waste gas treatment device is solved, and the technical effect of predicting the state of the industrial waste gas treatment device, realizing the synchronous monitoring of the industrial waste gas treatment device, assisting relevant personnel in operation and maintenance management, and timely eliminating device failures is achieved.

Description

Technical Field

[0001] The present invention relates to the field of digital processing technology, and in particular to a synchronous monitoring method and system based on industrial waste gas treatment. Background Art

[0002] At this stage, the continuous advancement of industrialization has caused serious damage to the natural environment. Industrial waste gas treatment is imminent, and the stability of industrial waste gas treatment equipment needs to be guaranteed. A real-time, efficient, and fast synchronous monitoring system can provide support for the operation and maintenance of industrial waste gas treatment equipment, timely eliminate faults in industrial waste gas treatment equipment, and ensure the stability of industrial waste gas treatment equipment. Directly using data acquisition devices for data collection will inevitably result in a certain delay.

[0003] In the prior art, there is a technical problem that the monitoring information of the industrial waste gas treatment device has a certain delay, resulting in the inability to timely perform operation and maintenance management of the industrial waste gas treatment device. Summary of the invention

[0004] The present application provides a synchronous monitoring method and system based on industrial waste gas treatment, which solves the technical problem that there is a certain time delay in the monitoring information of the industrial waste gas treatment device, resulting in the inability to timely perform operation and maintenance management of the industrial waste gas treatment device. The application achieves the technical effect of predicting the status of the industrial waste gas treatment device, realizing synchronous monitoring of the industrial waste gas treatment device, assisting relevant personnel in operation and maintenance management, and timely eliminating device failures.

[0005] In view of the above problems, the present application provides a synchronous monitoring method and system based on industrial waste gas treatment.

[0006] In the first aspect, the present application provides a synchronous monitoring method based on industrial waste gas treatment, wherein the method is applied to a synchronous monitoring system, and the system is communicatively connected with an intelligent industrial waste gas treatment system, and the method includes: retrieving an equipment operation index parameter set through the intelligent industrial waste gas treatment system; performing synchronous detection through the equipment operation index parameter set to obtain equipment status parameter information; obtaining a historical equipment operation index parameter set and a historical equipment status parameter information set; performing simulation operation through the equipment historical operation index parameter set and the equipment historical status parameter information set to construct an operation index-state parameter model; inputting the equipment operation index parameter set and the equipment status parameter information into the operation index-state parameter model to obtain equipment secondary state prediction information; performing equipment status detection in the next detection cycle through the data update frequency corresponding to the synchronous detection to obtain equipment secondary state detection information; comparing the equipment secondary state detection information with the equipment secondary state prediction information, and if the comparison passes, obtaining a synchronous online monitoring topology diagram of industrial waste gas treatment, wherein the operation index-state parameter model is embedded in the synchronous online monitoring topology diagram.

[0007] In the second aspect, the present application provides a synchronous monitoring system based on industrial waste gas treatment, wherein the system is communicatively connected to an intelligent industrial waste gas treatment system, and the system includes: a parameter retrieval unit, the parameter retrieval unit is used to retrieve a set of equipment operation index parameters through the intelligent industrial waste gas treatment system; a synchronous detection unit, the synchronous detection unit is used to perform synchronous detection through the equipment operation index parameter set to obtain equipment status parameter information; an information acquisition unit, the information acquisition unit is used to obtain a set of equipment historical operation index parameter sets and a set of equipment historical status parameter information; a simulation operation unit, the simulation operation unit is used to perform simulation operation through the equipment historical operation index parameter set and the equipment historical status parameter information set, and construct An operation index-state parameter model is constructed; a secondary state prediction unit is used to input the equipment operation index parameter set and the equipment state parameter information into the operation index-state parameter model to obtain equipment secondary state prediction information; a state detection unit is used to perform equipment state detection in the next detection cycle through the data update frequency corresponding to the synchronous detection to obtain equipment secondary state detection information; an information comparison unit is used to compare the equipment secondary state detection information with the equipment secondary state prediction information, and if the comparison is successful, a synchronous online monitoring topology diagram of industrial waste gas treatment is obtained, wherein the operation index-state parameter model is embedded in the synchronous online monitoring topology diagram.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0009] Due to the adoption of the intelligent system for industrial waste gas treatment, the equipment operation index parameter set is retrieved, synchronous detection is performed, and equipment status parameter information is obtained; the equipment historical operation index parameter set and the equipment historical status parameter information set are obtained to build an operation index-state parameter model; the equipment operation index parameter set and the equipment status parameter information are input into the operation index-state parameter model to obtain equipment secondary state prediction information; through synchronous detection of the corresponding data update frequency, in the next detection cycle, the equipment status is detected, the equipment secondary state detection information is obtained, and the equipment secondary state prediction information is compared, and if the comparison is passed, the synchronous online monitoring topology diagram of industrial waste gas treatment is obtained. The embodiment of the present application achieves the technical effect of predicting the state of the industrial waste gas treatment device, realizing the synchronous monitoring of the industrial waste gas treatment device, assisting relevant personnel in operation and maintenance management, and timely eliminating device failures. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A schematic flow chart of a synchronous monitoring method based on industrial waste gas treatment for this application;

[0011] Figure 2 A schematic diagram of a flow chart of constructing an operation index-state parameter model for a synchronous monitoring method based on industrial waste gas treatment in this application;

[0012] Figure 3 This is a structural schematic diagram of a synchronous monitoring system based on industrial waste gas treatment in this application.

[0013] Explanation of the reference numerals: parameter retrieving unit 11 , synchronization detection unit 12 , information acquiring unit 13 , simulation operation unit 14 , sub-state prediction unit 15 , state detection unit 16 , information comparing unit 17 . DETAILED DESCRIPTION

[0014] The present application provides a synchronous monitoring method and system based on industrial waste gas treatment, which solves the technical problem that there is a certain time delay in the monitoring information of the industrial waste gas treatment device, resulting in the inability to timely perform operation and maintenance management of the industrial waste gas treatment device. The application achieves the technical effect of predicting the status of the industrial waste gas treatment device, realizing synchronous monitoring of the industrial waste gas treatment device, assisting relevant personnel in operation and maintenance management, and timely eliminating device failures.

[0015] Embodiment 1

[0016] like Figure 1 As shown, the present application provides a synchronous monitoring method based on industrial waste gas treatment, wherein the method is applied to a synchronous monitoring system, the system is communicatively connected with an intelligent industrial waste gas treatment system, and the method includes:

[0017] Step S100: Retrieving a set of equipment operation index parameters through the industrial waste gas treatment intelligent system;

[0018] Step S200: Performing synchronous detection through the device operation indicator parameter set to obtain device status parameter information;

[0019] Specifically, the industrial waste gas treatment intelligent system is embedded in a cloud processor, and through the cloud connection between the industrial waste gas treatment intelligent system and the waste gas treatment device, the data of relevant waste gas treatment devices such as the activated carbon adsorption box, the acid-base absorption tower (spray tower), the acid mist absorption tower and the CO catalytic combustion equipment are synchronously imported into the industrial waste gas treatment intelligent system, and through the data retrieval instruction, the equipment operation index parameter set is retrieved in the industrial waste gas treatment intelligent system, and the equipment operation index parameter set includes but is not limited to the activated carbon adsorption box data, the acid-base absorption tower (spray tower), the acid mist absorption tower data, and the CO catalytic combustion equipment data. The activated carbon adsorption box, the acid-base absorption tower (spray tower), the acid mist absorption tower and the CO catalytic combustion equipment are synchronously detected to obtain equipment status parameter information, and the equipment status parameter information includes standby state parameters, operation state parameters, fault state parameters and other related state parameter information to provide data support for subsequent data processing.

[0020] Step S300: Acquire a device historical operation indicator parameter set and a device historical status parameter information set;

[0021] Step S400: Conduct simulation operation through the equipment historical operation index parameter set and the equipment historical status parameter information set to construct an operation index-status parameter model;

[0022] Specifically, through the industrial waste gas treatment intelligent system, data is retrieved to obtain the equipment's historical operating index parameter set and the equipment's historical status parameter information set. A subset of the equipment's historical operating index parameter set is the historical equipment operating index parameter set. An element of the equipment's historical status parameter information set is the historical equipment status parameter information. Based on the equipment's historical operating index parameter set and the equipment's historical status parameter information set, simulation training is performed to construct an operating index-status parameter model. The model basis of the operating index-status parameter model is a Markov chain, which provides a model basis for subsequent data processing.

[0023] Further, such as Figure 2 As shown, through the equipment historical operation index parameter set and the equipment historical status parameter information set, simulation operation is performed to construct an operation index-status parameter model, and the step S400 includes:

[0024] Step S410: dividing the device historical operation indicator parameter set through the device operation indicator parameter set to obtain a plurality of device historical operation indicator parameter subsets;

[0025] Step S420: dividing the device historical state parameter information set according to the device state parameter information to obtain multiple sets of device historical state parameter information;

[0026] Step S430: Based on the plurality of equipment historical operation indicator parameter subsets and the plurality of sets of equipment historical status parameter information, data grid mosaic is performed through the data update frequency to obtain a historical operation indicator-historical status parameter network;

[0027] Step S440: Conduct simulation operation through the historical operation index-historical state parameter network to construct an operation index-state parameter model.

[0028] Furthermore, through the historical operation index-historical state parameter network, simulation operation is performed to construct an operation index-state parameter model, and the step S440 further includes:

[0029] Step S441: randomly intercepting the historical operation index-historical state parameter network according to the data update frequency to obtain multiple historical operation index-historical state parameter random subnetworks;

[0030] Step S442: Conduct simulation operation through the multiple historical operation index-historical state parameter random subnets to build an operation index-state parameter sampling simulation model;

[0031] Step S443: Based on the operation index-state parameter sampling simulation model, a verification test is performed to determine the operation index-state parameter model.

[0032] Specifically, in order to comprehensively perform indicator analysis, it is necessary to optimize the distribution of the equipment historical operation indicator parameter set and the equipment historical status parameter information set, reset the information arrangement scheme in the equipment historical operation indicator parameter set according to the parameter distribution law of the equipment operation indicator parameter set, divide the equipment historical operation indicator parameter set, and obtain multiple equipment historical operation indicator parameter subsets, and the equipment historical operation indicator parameter subsets are consistent with the parameter distribution law of the equipment operation indicator parameter set; adopt a consistent technical solution to divide the equipment historical status parameter information set to obtain multiple groups of equipment historical status parameter information; determine multiple data update nodes according to the data update frequency, and based on the multiple equipment historical operation indicator parameter subsets and the multiple groups of equipment historical status parameter information, perform data grid mosaic according to the multiple data update nodes to obtain the historical operation indicator-historical status parameter network, the horizontal structure information of the historical operation indicator-historical status parameter network is multiple data update node information, and the vertical structure information of the historical operation indicator-historical status parameter network is the multiple equipment historical operation indicator parameter subsets and the multiple groups of equipment historical status parameter information mosaiced by the data grid, optimize the distribution of data, and facilitate subsequent data processing.

[0033] Specifically, in order to ensure the accuracy of the operation indicator-state parameter model while maximizing the operation processing efficiency, a random algorithm can be used to obtain a random node from the multiple data update nodes, and data can be intercepted in the historical operation indicator-historical state parameter network through the random node to obtain multiple historical operation indicator-historical state parameter random subnets; using multiple historical operation indicator-historical state parameter random subnets, based on the node numbers of the random nodes, simulated operations are performed to construct an operation indicator-state parameter sampling simulation model; the operation indicator-state parameter sampling simulation model is verified and tested, and after the verification test passes, the operation indicator-state parameter sampling simulation model is determined to be set as the operation indicator-state parameter model, so as to improve the training efficiency of the model by performing random sampling while ensuring the accuracy of the operation indicator-state parameter model.

[0034] Further, by performing simulation operation through the plurality of historical operation index-historical state parameter random subnets, an operation index-state parameter sampling simulation model is constructed, and the step S442 further includes:

[0035] Step S442-1: extracting data from the multiple historical operation index-historical status parameter random subnets through the multiple industrial waste gas treatment devices in the industrial waste gas treatment intelligent system to obtain historical status information of the industrial waste gas treatment devices;

[0036] Step S442-2: performing data mapping extraction through the historical status information to obtain the first historical status information, the first historical operation indicator parameter and the second historical status information;

[0037] Step S442-3: setting the first historical state information as current state information; setting the first historical operation indicator parameter as incentive information; setting the second historical state information as target state information;

[0038] Step S442-4: Based on the multiple historical operation indicators-historical state parameter random subnetworks, taking the Markov chain as the model basis, and through the current state information, the target state information and the incentive information, construct an operation indicator-state parameter sampling simulation model.

[0039] Specifically, multiple industrial waste gas treatment equipment in the industrial waste gas treatment intelligent system are determined, and the industrial waste gas treatment equipment is not limited to an activated carbon adsorption box, an acid-base absorption tower (spray tower), an acid mist absorption tower, a CO Catalytic combustion equipment, according to the equipment type, performs data extraction in the multiple historical operation index-historical state parameter random subnets to obtain historical state information of the industrial waste gas treatment equipment, the historical state information includes historical state and historical time node information, and the historical state includes standby state, operation state, and fault state; using the historical state information as identification data, in the multiple historical operation index-historical state parameter random subnets, performs data mapping extraction to obtain first historical state information, first historical operation index parameter and second historical state information, the sub-state of the first historical state information is the second historical state information, and the first historical operation index parameter is consistent with the historical time node information of the first historical operation index parameter; based on the Markov chain as the model basis, the first historical state information is set as the current state information; the first historical operation index parameter is set as the incentive information; the second historical state information is set as the target state information; state prediction is performed, based on the multiple historical operation index-historical state parameter random subnets, through the current state information, the target state information and the incentive information, the state prediction training is repeatedly performed, and the operation index-state parameter sampling simulation model is constructed to ensure the reliability of the operation index-state parameter sampling simulation model.

[0040] Further, based on the operation index-state parameter sampling simulation model, a verification test is performed to determine the operation index-state parameter model, and the step S443 further includes:

[0041] Step S443-1: performing random extraction in the historical operation index-historical state parameter network according to the data update frequency to obtain a plurality of random information of historical operation index-historical state parameters;

[0042] Step S443-2: inputting the plurality of historical operation index-historical state parameter random information into the operation index-state parameter sampling simulation model, and outputting a plurality of historical sub-state prediction information;

[0043] Step S443-3: performing comparison and verification in the historical operation index-historical state parameter network through the plurality of historical sub-state prediction information, and determining whether the comparison and verification result meets the preset model error threshold;

[0044] Step S443-4: If the comparison verification result meets the preset model error threshold, the operation index-state parameter sampling simulation model is set as the operation index-state parameter model.

[0045] Specifically, in order to ensure the accuracy of the operation indicator-state parameter model, a verification test is required. After the verification test, it can be determined whether the operation indicator-state parameter model meets the preset accuracy requirements. Through multiple data update nodes, random sampling is performed in the historical operation indicator-historical state parameter network to obtain multiple historical operation indicator-historical state parameter random information; the multiple historical operation indicator-historical state parameter random information is input into the operation indicator-state parameter sampling simulation model in turn to obtain the output of the operation indicator-state parameter sampling simulation model, and the output of the operation indicator-state parameter sampling simulation model is multiple historical sub-state prediction information; through multiple data update nodes, the multiple historical sub-state prediction information is compared and verified with the historical operation indicator-historical state parameter network to obtain the comparison and verification results. The preset model error threshold is a custom set parameter indicator, and it is judged whether the comparison and verification result meets the preset model error threshold; if it meets, the operation indicator-state parameter sampling simulation model is set as the operation indicator-state parameter model to provide support for ensuring that the accuracy of the operation indicator-state parameter model meets the preset accuracy requirements.

[0046] Step S500: inputting the equipment operation index parameter set and the equipment state parameter information into the operation index-state parameter model to obtain equipment secondary state prediction information;

[0047] Step S600: performing device status detection in the next detection cycle according to the data update frequency corresponding to the synchronous detection, and obtaining device secondary status detection information;

[0048] Specifically, when directly using data acquisition devices to collect data, there will inevitably be a certain amount of time delay. To ensure the efficiency of synchronous monitoring, an operation indicator-state parameter model is established to predict the sub-state of the equipment, and data detection is performed simultaneously. After the detection is completed, a comparison is performed to assist in obtaining equipment maintenance reminders, prepare equipment maintenance plans in advance, and provide support to ensure the working efficiency of industrial waste gas treatment equipment.

[0049] To further specify, the equipment operation index parameter set and the equipment state parameter information are input into the operation index-state parameter model to perform state prediction, obtain the output of the operation index-state parameter model, and set the output as the equipment sub-state prediction information; in the next detection cycle, the equipment state detection is synchronously performed to obtain the equipment sub-state detection information to provide data support for subsequent data processing.

[0050] Step S700: Compare the equipment sub-state detection information with the equipment sub-state prediction information. If the comparison is successful, obtain a synchronous online monitoring topology diagram of industrial waste gas treatment, wherein the operation indicator-state parameter model is embedded in the synchronous online monitoring topology diagram.

[0051] Furthermore, the operation index-state parameter model is embedded in the synchronous online monitoring topology map, and the step S700 further includes:

[0052] Step S710: Acquire equipment information of multiple industrial waste gas treatment equipment in the industrial waste gas treatment intelligent system;

[0053] Step S720: Based on the prediction process of the operation index-state parameter model, data binding is performed with the device information to generate a synchronous online monitoring topology map;

[0054] Step S730: The synchronous online monitoring topology diagram is synchronously displayed and outputted through the intelligent display module of the industrial waste gas treatment intelligent system.

[0055] Specifically, the equipment sub-state detection information is compared with the equipment sub-state prediction information. If the comparison is successful, a synchronous online monitoring topology diagram of industrial waste gas treatment is generated, in which the operation indicator-state parameter model is embedded. If the comparison fails, the corresponding equipment that fails the comparison is determined, and the corresponding equipment is judged to be abnormal, so as to provide support for assisting relevant managers of the synchronous monitoring system to perform equipment management.

[0056] To further specify, in the industrial waste gas treatment intelligent system, data extraction is performed to obtain equipment information of the multiple industrial waste gas treatment equipment, the equipment information including equipment model, equipment power, equipment auxiliary material filling information and other relevant data information; the prediction process of the operation indicator-state parameter model is associated with the equipment information to generate a synchronous online monitoring topology map; the intelligent display module of the industrial waste gas treatment intelligent system is used to synchronously display and output the synchronous online monitoring topology map to assist relevant management personnel of the synchronous monitoring system to perform equipment maintenance and inspection, and the synchronous online monitoring topology map is synchronously displayed through the intelligent display module to improve the convenience of synchronous monitoring system management.

[0057] In summary, the synchronous monitoring method and system based on industrial waste gas treatment provided by this application have the following technical effects:

[0058] Due to the adoption of the intelligent system for industrial waste gas treatment, the equipment operation index parameter set is retrieved, synchronous detection is performed, and equipment status parameter information is obtained; the equipment historical operation index parameter set and the equipment historical status parameter information set are obtained to build an operation index-state parameter model; the equipment operation index parameter set and the equipment status parameter information are input into the operation index-state parameter model to obtain equipment secondary state prediction information; through synchronous detection of the corresponding data update frequency, in the next detection cycle, the equipment status is detected, the equipment secondary state detection information is obtained, and the equipment secondary state prediction information is compared, and if the comparison is passed, the synchronous online monitoring topology diagram of industrial waste gas treatment is obtained. This application provides a synchronous monitoring method and system based on industrial waste gas treatment, which achieves the technical effect of predicting the state of industrial waste gas treatment equipment, realizing synchronous monitoring of industrial waste gas treatment equipment, assisting relevant personnel in operation and maintenance management, and timely eliminating device failures.

[0059] By adopting the data update frequency, random interception is performed in the historical operation index-historical state parameter network, multiple historical operation index-historical state parameter random subnetworks are obtained, simulation operation is performed, and an operation index-state parameter sampling simulation model is constructed. Verification tests are performed to determine the operation index-state parameter model. While ensuring the accuracy of the operation index-state parameter model, the training efficiency of the model is improved by performing random sampling.

[0060] Due to the adoption of data update frequency, random extraction is performed in the historical operation index-historical state parameter network, multiple historical operation index-historical state parameter random information is obtained, input into the operation index-state parameter sampling simulation model, multiple historical sub-state prediction information is output, and comparison and verification are performed in the historical operation index-historical state parameter network to determine whether the comparison and verification results meet the preset model error threshold; if so, the operation index-state parameter model is determined. Support is provided to ensure that the accuracy of the operation index-state parameter model meets the preset accuracy requirements.

[0061] Embodiment 2

[0062] Based on the same inventive concept as the synchronous monitoring method based on industrial waste gas treatment in the aforementioned embodiment, Figure 3 As shown, the present application provides a synchronous monitoring system based on industrial waste gas treatment, the system is communicatively connected with the industrial waste gas treatment intelligent system, and the system includes:

[0063] A parameter retrieving unit 11, wherein the parameter retrieving unit 11 is used to retrieve a parameter set of equipment operation indicators through the industrial waste gas treatment intelligent system;

[0064] A synchronization detection unit 12, the synchronization detection unit 12 is used to perform synchronization detection through the device operation indicator parameter set to obtain device status parameter information;

[0065] An information acquisition unit 13, the information acquisition unit 13 is used to acquire a device historical operation indicator parameter set and a device historical status parameter information set;

[0066] A simulation operation unit 14, the simulation operation unit 14 is used to perform simulation operation through the equipment historical operation index parameter set and the equipment historical state parameter information set to construct an operation index-state parameter model;

[0067] A secondary state prediction unit 15, the secondary state prediction unit 15 is used to input the equipment operation index parameter set and the equipment state parameter information into the operation index-state parameter model to obtain equipment secondary state prediction information;

[0068] A state detection unit 16, the state detection unit 16 is used to perform device state detection in the next detection cycle through the data update frequency corresponding to the synchronous detection, and obtain device secondary state detection information;

[0069] The information comparison unit 17 is used to compare the equipment sub-state detection information with the equipment sub-state prediction information. If the comparison is successful, a synchronous online monitoring topology diagram of industrial waste gas treatment is obtained, wherein the operation indicator-state parameter model is embedded in the synchronous online monitoring topology diagram.

[0070] Furthermore, the system comprises:

[0071] A parameter set division unit, the parameter set division unit is used to divide the device historical operation indicator parameter set through the device operation indicator parameter set to obtain multiple device historical operation indicator parameter subsets;

[0072] A state parameter information acquisition unit, the state parameter information acquisition unit is used to divide the device historical state parameter information set according to the device state parameter information, and acquire multiple sets of device historical state parameter information;

[0073] A data grid mosaic unit, the data grid mosaic unit is used to perform data grid mosaic based on the plurality of equipment historical operation indicator parameter subsets and the plurality of sets of equipment historical status parameter information through the data update frequency to obtain a historical operation indicator-historical status parameter network;

[0074] A simulation operation unit is used to perform simulation operation through the historical operation index-historical state parameter network to construct an operation index-state parameter model.

[0075] Furthermore, the system comprises:

[0076] A random interception unit, the random interception unit is used to perform random interception in the historical operation indicator-historical state parameter network according to the data update frequency, and obtain multiple historical operation indicator-historical state parameter random subnetworks;

[0077] A simulation operation unit, the simulation operation unit is used to perform simulation operation through the multiple historical operation index-historical state parameter random subnets to build an operation index-state parameter sampling simulation model;

[0078] A verification test unit is used to perform a verification test based on the operation index-state parameter sampling simulation model to determine the operation index-state parameter model.

[0079] Furthermore, the system comprises:

[0080] A data extraction unit, the data extraction unit is used to extract data in the multiple historical operation indicators-historical state parameter random subnets through multiple industrial waste gas treatment equipment in the industrial waste gas treatment intelligent system, and obtain historical state information of the industrial waste gas treatment equipment;

[0081] A data mapping extraction unit, the data mapping extraction unit is used to perform data mapping extraction through the historical state information to obtain the first historical state information, the first historical operation indicator parameter and the second historical state information;

[0082] An information setting unit, the information setting unit is used to set the first historical state information as current state information; set the first historical operation indicator parameter as incentive information; set the second historical state information as target state information;

[0083] A model building unit is used to build an operation indicator-state parameter sampling simulation model based on the multiple historical operation indicators-historical state parameter random subnetworks, with Markov chain as the model basis, through the current state information, the target state information and the incentive information.

[0084] Furthermore, the system comprises:

[0085] A random extraction unit, the random extraction unit is used to perform random extraction in the historical operation index-historical state parameter network according to the data update frequency, and obtain a plurality of random information of historical operation index-historical state parameters;

[0086] A state prediction output unit, the state prediction output unit is used to input the plurality of historical operation index-historical state parameter random information into the operation index-state parameter sampling simulation model, and output a plurality of historical sub-state prediction information;

[0087] A comparison and verification unit, the comparison and verification unit is used to compare and verify the historical operation index-historical state parameter network through the plurality of historical sub-state prediction information, and determine whether the comparison and verification result meets a preset model error threshold;

[0088] A setting unit, wherein the setting unit is used to set the operation index-state parameter sampling simulation model as the operation index-state parameter model if the comparison verification result meets a preset model error threshold.

[0089] Furthermore, the system comprises:

[0090] An equipment information acquisition unit, the equipment information acquisition unit is used to acquire equipment information of multiple industrial waste gas treatment equipment in the industrial waste gas treatment intelligent system;

[0091] A data binding unit, the data binding unit is used to perform data binding with the device information based on the prediction process of the operation indicator-state parameter model to generate a synchronous online monitoring topology map;

[0092] A synchronous display output unit is used to synchronously display and output the synchronous online monitoring topology diagram through the intelligent display module of the industrial waste gas treatment intelligent system.

[0093] This specification and drawings are merely exemplary illustrations of the present application, and various modifications and combinations may be made thereto without departing from the spirit and scope of the present application. These modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, and the present application intends to include these modifications and variations.

Claims

1. A synchronous monitoring method based on industrial waste gas treatment, characterized in that: The method is applied to a synchronous monitoring system, the system is communicatively connected with an intelligent system for industrial waste gas treatment, and the method comprises: Retrieving a set of equipment operation index parameters through the industrial waste gas treatment intelligent system; Through the equipment operation indicator parameter set, synchronous detection is performed to obtain equipment status parameter information; Obtain the equipment's historical operating indicator parameter set and equipment's historical status parameter information set; Conduct simulation operation through the equipment historical operation index parameter set and the equipment historical status parameter information set to construct an operation index-status parameter model; Inputting the equipment operation index parameter set and the equipment state parameter information into the operation index-state parameter model to obtain equipment secondary state prediction information; By using the data update frequency corresponding to the synchronous detection, in the next detection cycle, the device status detection is performed to obtain the device secondary status detection information; Comparing the equipment secondary state detection information with the equipment secondary state prediction information, if the comparison is successful, obtaining a synchronous online monitoring topology diagram of industrial waste gas treatment, wherein the operation index-state parameter model is embedded in the synchronous online monitoring topology diagram; Among them, through the equipment historical operation index parameter set and the equipment historical status parameter information set, simulated operation is performed to construct an operation index-status parameter model, and the method includes: By using the equipment operation index parameter set, the equipment historical operation index parameter set is divided to obtain a plurality of equipment historical operation index parameter subsets; Dividing the device historical state parameter information set according to the device state parameter information to obtain multiple sets of device historical state parameter information; Based on the plurality of equipment historical operation index parameter subsets and the plurality of sets of equipment historical status parameter information, data grid mosaic is performed through the data update frequency to obtain a historical operation index-historical status parameter network; Through the historical operation index-historical state parameter network, simulation operation is carried out to construct an operation index-state parameter model.

2. The method according to claim 1, characterized in that Through the historical operation index-historical state parameter network, simulated operation is performed to construct an operation index-state parameter model, and the method further includes: According to the data update frequency, random interception is performed in the historical operation index-historical state parameter network to obtain multiple historical operation index-historical state parameter random subnetworks; Through the multiple historical operation indicators-historical state parameter random subnets, simulated operation is performed to build an operation indicator-state parameter sampling simulation model; Based on the operation index-state parameter sampling simulation model, a verification test is performed to determine the operation index-state parameter model.

3. The method according to claim 2, characterized in that By using the plurality of historical operation index-historical state parameter random subnets, a simulation operation is performed to construct an operation index-state parameter sampling simulation model, and the method further comprises: Through the multiple industrial waste gas treatment equipment in the industrial waste gas treatment intelligent system, data is extracted in the multiple historical operation indicators-historical status parameter random subnets to obtain historical status information of the industrial waste gas treatment equipment; Through the historical status information, data mapping extraction is performed to obtain the first historical status information, the first historical operation indicator parameter and the second historical status information; The first historical state information is set as current state information; the first historical operation index parameter is set as incentive information; the second historical state information is set as target state information; Based on the multiple historical operation indicators-historical state parameter random subnetworks, taking Markov chain as the model basis, through the current state information, the target state information and the incentive information, an operation indicator-state parameter sampling simulation model is constructed.

4. The method according to claim 2, characterized in that Based on the operation index-state parameter sampling simulation model, a verification test is performed to determine the operation index-state parameter model, and the method further includes: According to the data update frequency, random extraction is performed in the historical operation index-historical state parameter network to obtain a plurality of random information of historical operation index-historical state parameters; Inputting the plurality of historical operation index-historical state parameter random information into the operation index-state parameter sampling simulation model, and outputting a plurality of historical sub-state prediction information; By using the plurality of historical sub-state prediction information, comparison and verification are performed in the historical operation index-historical state parameter network to determine whether the comparison and verification result meets the preset model error threshold; If the comparison and verification result meets the preset model error threshold, the operation index-state parameter sampling simulation model is set as the operation index-state parameter model.

5. The method according to claim 1, characterized in that The operation indicator-state parameter model is embedded in the synchronous online monitoring topology graph, and the method further comprises: Acquire equipment information of multiple industrial waste gas treatment equipment in the industrial waste gas treatment intelligent system; Based on the prediction process of the operation index-state parameter model, data binding is performed with the device information to generate a synchronous online monitoring topology map; The synchronous online monitoring topology diagram is synchronously displayed and outputted through the intelligent display module of the industrial waste gas treatment intelligent system.

6. A synchronous monitoring system based on industrial waste gas treatment, characterized in that: The system is used to implement the method described in any one of claims 1 to 5, the system is communicatively connected with an intelligent industrial waste gas treatment system, and the system comprises: A parameter retrieving unit, the parameter retrieving unit is used to retrieve a parameter set of equipment operation indicators through the industrial waste gas treatment intelligent system; A synchronization detection unit, the synchronization detection unit is used to perform synchronization detection through the device operation indicator parameter set to obtain device status parameter information; An information acquisition unit, the information acquisition unit is used to acquire a device historical operation indicator parameter set and a device historical status parameter information set; A simulation operation unit, the simulation operation unit is used to perform simulation operation through the equipment historical operation index parameter set and the equipment historical state parameter information set to construct an operation index-state parameter model; A secondary state prediction unit, the secondary state prediction unit is used to input the equipment operation index parameter set and the equipment state parameter information into the operation index-state parameter model to obtain equipment secondary state prediction information; A state detection unit, the state detection unit is used to perform device state detection in the next detection cycle through the data update frequency corresponding to the synchronous detection, and obtain device secondary state detection information; An information comparison unit is used to compare the equipment sub-state detection information with the equipment sub-state prediction information. If the comparison is successful, a synchronous online monitoring topology diagram of industrial waste gas treatment is obtained, wherein the operation indicator-state parameter model is embedded in the synchronous online monitoring topology diagram.

Images