CN114638412A - Hazardous waste disposal capacity early warning method and device, electronic equipment and storage medium - Google Patents
Hazardous waste disposal capacity early warning method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN114638412A CN114638412A CN202210241399.7A CN202210241399A CN114638412A CN 114638412 A CN114638412 A CN 114638412A CN 202210241399 A CN202210241399 A CN 202210241399A CN 114638412 A CN114638412 A CN 114638412A
- Authority
- CN
- China
- Prior art keywords
- hazardous waste
- predicted value
- neural network
- weekly
- measurement
- 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
- 239000002920 hazardous waste Substances 0.000 title claims abstract description 319
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000003860 storage Methods 0.000 title claims abstract description 13
- 238000005259 measurement Methods 0.000 claims abstract description 159
- 230000003442 weekly effect Effects 0.000 claims abstract description 88
- 238000013528 artificial neural network Methods 0.000 claims abstract description 83
- 230000004927 fusion Effects 0.000 claims abstract description 46
- 238000004364 calculation method Methods 0.000 claims abstract description 40
- 239000002699 waste material Substances 0.000 claims description 149
- 238000003062 neural network model Methods 0.000 claims description 56
- 238000012545 processing Methods 0.000 claims description 47
- 238000012549 training Methods 0.000 claims description 24
- 230000006870 function Effects 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 8
- 238000012546 transfer Methods 0.000 claims description 8
- 210000002569 neuron Anatomy 0.000 claims description 5
- 210000004205 output neuron Anatomy 0.000 claims description 4
- 230000000737 periodic effect Effects 0.000 claims description 2
- 230000002354 daily effect Effects 0.000 description 84
- 238000012937 correction Methods 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 8
- 238000013473 artificial intelligence Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 238000010606 normalization Methods 0.000 description 6
- 238000012360 testing method Methods 0.000 description 6
- 238000001914 filtration Methods 0.000 description 5
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000003203 everyday effect Effects 0.000 description 3
- 230000007774 longterm Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 238000009825 accumulation Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000006378 damage Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000002689 soil Substances 0.000 description 2
- 208000005623 Carcinogenesis Diseases 0.000 description 1
- 208000005374 Poisoning Diseases 0.000 description 1
- 208000031320 Teratogenesis Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000036952 cancer formation Effects 0.000 description 1
- 231100000504 carcinogenesis Toxicity 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 230000037406 food intake Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000029052 metamorphosis Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 231100000572 poisoning Toxicity 0.000 description 1
- 230000000607 poisoning effect Effects 0.000 description 1
- 230000037384 skin absorption Effects 0.000 description 1
- 231100000274 skin absorption Toxicity 0.000 description 1
- 238000011272 standard treatment Methods 0.000 description 1
- 230000001988 toxicity Effects 0.000 description 1
- 231100000419 toxicity Toxicity 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- General Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Development Economics (AREA)
- Biophysics (AREA)
- General Business, Economics & Management (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Primary Health Care (AREA)
- Processing Of Solid Wastes (AREA)
Abstract
The invention provides a hazardous waste disposal capability early warning method and device, electronic equipment and a computer readable storage medium. The method comprises the following steps: inputting first preset historical hazardous waste treatment data to a neural network daily measurement model to obtain a daily measurement hazardous waste treatment amount predicted value and a daily measurement hazardous waste output amount predicted value of a prediction day; inputting second preset historical hazardous waste treatment data to the neural network weekly measurement model according to the week number of the prediction day to obtain a weekly measurement hazardous waste treatment amount prediction value and a weekly measurement hazardous waste output amount prediction value of the prediction day; respectively performing fusion calculation on the predicted value of the daily-measured hazardous waste disposal quantity and the predicted value of the weekly-measured hazardous waste disposal quantity, and the predicted value of the daily-measured hazardous waste output quantity and the predicted value of the weekly-measured hazardous waste output quantity to obtain a final predicted value of the hazardous waste disposal quantity and a final predicted value of the predicted hazardous waste output quantity; and determining whether to perform early warning or not according to the final predicted value of the hazardous waste disposal quantity and the final predicted value of the predicted hazardous waste output quantity. The method provided by the invention realizes the early warning of hazardous waste disposal capacity.
Description
Technical Field
The invention relates to the technical field of hazardous waste disposal, in particular to a hazardous waste disposal capability early warning method, a hazardous waste disposal capability early warning device, electronic equipment and a computer readable storage medium.
Background
The hazardous waste is hazardous waste, and with the development of industry, the hazardous waste discharged in the industrial production process is increasing. The dangerous waste is discharged at will, and the stored dangerous waste pollutes water and soil under the long-term permeation and diffusion effects of rainwater and underground water, reduces the environmental function level of regions and influences human health. Meanwhile, hazardous waste can cause toxicity through ingestion, inhalation, skin absorption and eye contact, and can also cause dangerous events such as burning, explosion and the like. The long-term harm of hazardous waste includes long-term poisoning, carcinogenesis, teratogenesis, and metamorphosis caused by repeated contact. The pollution of atmosphere, water source, soil and the like caused by the non-treatment or non-standard treatment and disposal of hazardous wastes can become a bottleneck for restricting economic activities.
At present, the hazardous waste disposal quantity and the hazardous waste output quantity in a city are not fixed, if the current hazardous waste output quantity in the city exceeds the current hazardous waste disposal quantity of a hazardous waste enterprise, namely the hazardous waste disposal capacity is not enough to dispose the hazardous waste output quantity, the hazardous waste accumulation in the city can be caused, and the natural ecological environment of the city is influenced.
Disclosure of Invention
The invention aims to provide a method, a device, electronic equipment and a computer readable storage medium for early warning of hazardous waste disposal capacity, and aims to solve the technical problem that the hazardous waste disposal capacity cannot be early warned in the prior art.
The technical scheme of the invention is as follows, and provides a dangerous waste disposal capacity early warning method, which comprises the following steps:
inputting first preset historical hazardous waste treatment data to a neural network daily measurement model to obtain a daily measurement hazardous waste disposal quantity predicted value and a daily measurement hazardous waste output quantity predicted value of a prediction day, wherein the neural network daily measurement model is a neural network model for predicting daily hazardous waste disposal quantity at intervals of 1 day;
inputting second preset historical hazardous waste treatment data to a neural network weekly measuring model according to the week number of the prediction day to obtain a weekly measuring hazardous waste treatment amount prediction value and a weekly measuring hazardous waste output amount prediction value of the prediction day, wherein the neural network weekly measuring model is a neural network model for predicting weekly and daily hazardous waste treatment amounts at intervals of 7 days;
respectively carrying out fusion calculation on the predicted value of the daily-measured hazardous waste disposal quantity and the predicted value of the weekly-measured hazardous waste disposal quantity and the predicted value of the daily-measured hazardous waste output quantity and the predicted value of the weekly-measured hazardous waste output quantity to obtain a final predicted value of the hazardous waste disposal quantity and a final predicted value of the predicted hazardous waste output quantity;
and determining whether to perform early warning or not according to the final predicted value of the hazardous waste disposal quantity and the final predicted value of the predicted hazardous waste output quantity.
Optionally, the first preset historical hazardous waste treatment data includes hazardous waste receiving amount, hazardous waste disposal amount, hazardous waste output amount and corresponding date type of a hazardous waste enterprise for a plurality of consecutive days before a prediction date; the second preset historical dangerous waste treatment data comprises dangerous waste receiving quantity, dangerous waste disposal quantity, dangerous waste output quantity and corresponding date types of dangerous waste enterprises of which the weeks are the same as the predicted days in a plurality of continuous weeks before the predicted days, wherein the date types are one of holidays and non-holidays.
Optionally, the method for early warning of hazardous waste disposal capability further includes normalizing the hazardous waste receiving capacity, the hazardous waste disposal capacity, and the hazardous waste output capacity before inputting the first preset historical hazardous waste processing data into the neural network daily measurement model and inputting the second preset historical hazardous waste processing data into the neural network circumferential measurement model.
Optionally, the training step of the neural network daily measurement model includes: determining an input layer node unit vector, a hidden layer node unit vector, a feedback state vector and an output layer node vector of the neural network, and constructing a neural network model;
calculating the error of the neural network model according to first preset historical hazardous waste treatment data input to the neural network model, and updating the parameters of the neural network according to the error of the neural network model;
and when the error of the neural network model is within a preset range, finishing the training of the neural network model to obtain the daily measurement model of the neural network.
Optionally, the nonlinear state space expression of the neural network model is
y(k)=g(w3l(k))
l(k)=f(w1c(k)+w2(x(k)))
c(k)=l(k-1)
Wherein y (k) represents the output level node vector, l (k) represents the hidden level node element vector, x (k) represents the input vector, c (k) represents the feedback state vector, w3Representing the connection weight, w, from the hidden layer to the output layer2Representing the connection weight, w, of the input layer to the hidden layer1Representing the connection weights of the socket layer to the hidden layer, g (×) representing the transfer function of the output neurons, and f (×) representing the transfer function of the hidden layer neurons.
Optionally, the method for fusion calculation of the daily measurement predicted value of the treatment amount of the hazardous waste and the daily measurement predicted value of the output amount of the hazardous waste with the weekly measurement predicted value of the treatment amount of the hazardous waste and the weekly measurement predicted value of the output amount of the hazardous waste respectively includes:
carrying out fusion calculation on the predicted value of the daily measured hazardous waste disposal quantity and the predicted value of the weekly measured hazardous waste disposal quantity by utilizing a fusion calculation formula, and carrying out fusion calculation on the predicted value of the daily measured hazardous waste output quantity and the predicted value of the weekly measured hazardous waste output quantity by utilizing the fusion calculation formula, wherein the fusion calculation formula is that Y is alpha Ydi+β*YwiWherein i is 1,2, and Y isd1For daily measurement of the predicted value of the amount of the hazardous waste, Yw1For weekly measurement of the predicted value of the amount of hazardous waste disposal, Yd2For daily measurement of the output predicted value of dangerous waste, Yw2The predicted value of the output of the weekly-detected dangerous waste is obtained, and alpha and beta are parameters.
Optionally, according to the final predicted value of the hazardous waste disposal quantity and the final predicted value of the predicted hazardous waste output quantity, whether to perform early warning is determined, and the method specifically comprises the following steps: and if the ratio of the final predicted value of the hazardous waste disposal quantity to the final predicted value of the predicted hazardous waste output quantity is greater than a set threshold value, alarming, otherwise, not alarming.
According to another technical scheme, the method for early warning of the hazardous waste disposal capacity comprises a daily measurement prediction module, a weekly measurement prediction module, a fusion prediction module and an early warning module;
the daily measurement prediction module is used for inputting first preset historical hazardous waste treatment data to the neural network daily measurement model to obtain a daily measurement hazardous waste treatment amount prediction value and a daily measurement hazardous waste output amount prediction value of a prediction day, and the neural network daily measurement model is a neural network model for predicting daily hazardous waste treatment amounts at intervals of 1 day;
the weekly measurement prediction module is used for inputting second preset historical hazardous waste treatment data to the neural network weekly measurement model according to the fact that the prediction day is the day of the week to obtain a weekly measurement hazardous waste disposal quantity prediction value and a weekly measurement hazardous waste output quantity prediction value of the prediction day, and the neural network weekly measurement model is a neural network model for predicting the weekly and same-day hazardous waste disposal quantity at intervals of 7 days;
the fusion prediction module is used for performing fusion calculation on the daily measurement hazardous waste treatment amount predicted value and the daily measurement hazardous waste output amount predicted value and the weekly measurement hazardous waste treatment amount predicted value and the weekly measurement hazardous waste output amount predicted value respectively to obtain a final predicted value of the predicted hazardous waste treatment amount and a final predicted value of the predicted hazardous waste output amount;
and the early warning module is used for determining whether to carry out early warning according to the final predicted value of the predicted hazardous waste treatment amount and the final predicted value of the predicted hazardous waste output amount.
Another technical solution of the present invention is as follows, an electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the hazardous waste disposal capability early warning method according to any one of the above technical solutions when executing the computer program.
Another aspect of the present invention is a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the method for warning hazardous waste disposal capability according to any of the above methods is implemented.
The invention has the beneficial effects that: inputting first preset historical hazardous waste treatment data to a neural network daily measurement model to obtain a daily measurement hazardous waste disposal quantity predicted value and a daily measurement hazardous waste output quantity predicted value of a prediction day, wherein the neural network daily measurement model is a neural network model for predicting daily hazardous waste disposal quantity at intervals of 1 day; inputting second preset historical hazardous waste treatment data to a neural network weekly measuring model according to the week number of the prediction day to obtain a weekly measuring hazardous waste treatment amount prediction value and a weekly measuring hazardous waste output amount prediction value of the prediction day, wherein the neural network weekly measuring model is a neural network model for predicting weekly and daily hazardous waste treatment amounts at intervals of 7 days; respectively carrying out fusion calculation on the predicted value of the daily-measured hazardous waste disposal quantity and the predicted value of the weekly-measured hazardous waste disposal quantity and the predicted value of the daily-measured hazardous waste output quantity and the predicted value of the weekly-measured hazardous waste output quantity to obtain a final predicted value of the hazardous waste disposal quantity and a final predicted value of the predicted hazardous waste output quantity; determining whether to perform early warning or not according to the final predicted value of the hazardous waste disposal quantity and the final predicted value of the predicted hazardous waste output quantity; through the mode, the current hazardous waste disposal quantity and the hazardous waste output quantity are predicted, and the early warning of the hazardous waste disposal capacity is realized, so that the natural ecological environment of a city is protected.
Drawings
Fig. 1 is a schematic flow chart illustrating a hazardous waste disposal capability early warning method according to a first embodiment of the present invention;
fig. 2 is a schematic structural diagram of a hazardous waste disposal capability early warning device according to a second embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device according to a third embodiment of the invention;
fig. 4 is a schematic structural diagram of a storage medium according to a fourth embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the invention. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
Fig. 1 is a flowchart illustrating a hazardous waste disposal capability early warning method according to a first embodiment of the present invention. It should be noted that the method of the present invention is not limited to the flow sequence shown in fig. 1 if the results are substantially the same. As shown in fig. 1, the method for early warning of hazardous waste disposal capability mainly includes the following steps:
s101, inputting first preset historical hazardous waste treatment data to a neural network daily measurement model to obtain a daily measurement hazardous waste treatment amount predicted value and a hazardous waste output amount predicted value of a prediction day, wherein the neural network daily measurement model is a neural network model for predicting daily hazardous waste treatment amounts at intervals of 1 day;
in an optional embodiment, the first preset historical hazardous waste treatment data comprises the hazardous waste receiving amount, the hazardous waste disposal amount, the hazardous waste output amount and the corresponding date type of a hazardous waste enterprise continuously multiple days before a prediction day; the second preset historical dangerous waste treatment data comprises dangerous waste receiving amount, dangerous waste disposal amount, dangerous waste output amount and corresponding date types of dangerous waste enterprises of which the weeks before the prediction day are the same as the week of the prediction day, wherein the date types are one of holidays and non-holidays.
It should be noted that the date type corresponding to the multiple consecutive days before the predicted day in the first preset historical critical waste processing data is the date type corresponding to each of the multiple consecutive days, and the date types are holidays and non-holidays, and because there is a large difference between the critical waste processing amount of the holidays and the non-holidays, the date type is added to the input data of the neural network model. The number of consecutive days before the predicted day may be a preset number of days, for example, four or five days.
When the hazardous waste receiving quantity, the disposal quantity and the hazardous waste output quantity of the hazardous waste enterprise are obtained, the range of the hazardous waste disposal enterprise needing to be visited and investigated is needed to be defined, the monthly hazardous waste receiving quantity, the monthly hazardous waste disposal quantity and the monthly hazardous waste output quantity of the hazardous waste disposal enterprise are counted, data filtering is carried out on the obtained original hazardous waste receiving quantity, the acquired hazardous waste disposal quantity and the acquired hazardous waste output quantity, invalid data are removed, and filtered historical data are obtained.
The average value of the dangerous waste receiving quantity, the dangerous waste processing quantity and the dangerous waste output quantity of the dangerous waste processing enterprise is calculated according to the filtered historical data, the average value of the dangerous waste receiving quantity, the dangerous waste processing quantity and the dangerous waste output quantity at the moment is respectively removed from the average value of the original dangerous waste receiving quantity, the dangerous waste processing quantity and the dangerous waste output quantity before filtering, and a dangerous waste receiving quantity correction index, a dangerous waste processing quantity and a dangerous waste output quantity correction index are respectively obtained.
In a specific embodiment, the filtered historical hazardous waste receiving quantity, hazardous waste disposal quantity and hazardous waste output quantity are corrected through the hazardous waste receiving quantity correction index, the hazardous waste disposal quantity correction index and the hazardous waste output quantity correction index, and the filtered historical hazardous waste receiving quantity, hazardous waste disposal quantity and hazardous waste output quantity are correspondingly removed from the hazardous waste receiving quantity correction index, the hazardous waste disposal quantity correction index and the hazardous waste output quantity correction index respectively, so that the hazardous waste receiving quantity, the hazardous waste disposal quantity and the hazardous waste output quantity of the hazardous waste enterprise continuously for multiple days before the prediction date in the first preset historical hazardous waste processing data can be obtained. Because the historical dangerous waste receiving quantity, the dangerous waste processing quantity and the dangerous waste output quantity after filtering have errors with the original historical dangerous waste receiving quantity, the original dangerous waste processing quantity and the original dangerous waste output quantity, the errors are reduced for improving the accuracy of the historical dangerous waste receiving quantity, the historical dangerous waste processing quantity and the original dangerous waste output quantity after filtering, and therefore the historical dangerous waste receiving quantity, the historical dangerous waste processing quantity and the historical dangerous waste output quantity after filtering are corrected.
In an optional embodiment, the training step of the neural network daily measurement model includes:
determining an input layer node unit vector, a hidden layer node unit vector, a feedback state vector and an output layer node vector of the neural network, and constructing a neural network model;
calculating the error of the neural network model according to first preset historical hazardous waste treatment data input to the neural network model, and updating the parameters of the neural network according to the error of the neural network model;
and when the error of the neural network model is within a preset range, finishing the training of the neural network model to obtain the daily measurement model of the neural network.
When a neural network model is constructed and trained, input and output data of the neural network need to be determined, and the optimal number of neurons in the hidden layer needs to be determined. The neural network model may be an elman-based neural network model, which is a neural network model proposed for speech processing, and is a typical local regression network (global feed for forward local regression) model. During specific implementation, the dangerous waste receiving quantity, the dangerous waste disposal quantity, the dangerous waste output quantity and the corresponding date type of a dangerous waste enterprise continuously for a plurality of days before the prediction date are used as the input of the elman-based neural network model, and the predicted daily dangerous waste disposal quantity and the predicted daily dangerous waste output quantity are used as the output of the elman-based neural network model.
In an alternative embodiment, the neural network model has a non-linear state space expression of
y(k)=g(w3l(k))
l(k)=f(w1c(k)+w2(x(k)))
c(k)=l(k-1)
Wherein y (k) represents the output level node vector, l (k) represents the hidden level node unit vector, x (k) represents the input vector, c (k) represents the feedback state vector, w3Representing the connection weight, w, from the hidden layer to the output layer2Representing the connection weight, w, of the input layer to the hidden layer1Representing the connection weights of the socket layer to the hidden layer, g (×) representing the transfer function of the output neurons, and f (×) representing the transfer function of the hidden layer neurons.
Wherein, the weight value is updated by using an error back propagation algorithm, and the index function is learned by using an error sum of squares function, and the formula of the index function learning isThe E (w) represents an index function, yk(w) represents a target input vector.
S102, inputting second preset historical hazardous waste treatment data to the neural network weekly measurement model according to the week number of the prediction day to obtain a weekly measurement hazardous waste treatment amount prediction value and a hazardous waste output amount prediction value of the prediction day; the neural network weekly measurement model is a neural network model for predicting the daily dangerous waste disposal quantity every week at intervals of 7 days;
in an optional embodiment, the method for early warning of hazardous waste disposal capability further includes normalizing the hazardous waste receiving capacity, the hazardous waste disposal capacity, and the hazardous waste output capacity before inputting the first preset historical hazardous waste processing data into the neural network daily measurement model and before inputting the second preset historical hazardous waste processing data into the neural network circumferential measurement model.
The method comprises the following steps of utilizing a normalization processing formula to perform normalization processing on historical hazardous waste processing data, wherein the normalization processing formula isXkRepresenting the value of the kth parameter, x, in a sequence of historical critical waste treatment datamaxRepresents xkMaximum value, x in data sequence of historical hazardous waste treatment dataminRepresents xkAnd (4) the minimum value in the data sequence of the historical hazardous waste treatment data.
After the normalization processing is carried out on the historical dangerous waste processing data, the normalized data are processed into an input format required by a neural network daily measurement model and a neural network weekly measurement model, and the input format of the neural network daily measurement model data is [ n ]1 n2n3…nk m1 m2 m3…mk L1 L2 L3…Lk a1 a2 a3…ak]Where k represents the number of data selection days, e.g. n1、n2、n3…nkRespectively represents the dangerous waste receiving capacity m of the dangerous waste enterprise in k days1、m2、m3…mkHazardous waste disposal quantity, L, of hazardous waste enterprises in k days respectively1、L2、L3…LkRespectively represents the dangerous waste output quantity of the dangerous waste enterprise in k days, a1、a2、a3…akRespectively, the date type corresponding to k days. In specific implementation, if the dangerous waste receiving amount, the dangerous waste disposal amount, the dangerous waste output amount and the corresponding date type of the first five days are used for predicting the dangerous waste disposal amount predicted value and the dangerous waste output amount predicted value of the sixth day, k is 5. And if the dangerous waste receiving quantity, the dangerous waste disposal quantity, the dangerous waste output quantity and the corresponding date type of the first six days before use predict the dangerous waste disposal quantity predicted value and the dangerous waste output quantity predicted value of the seventh day, k is 6.
In a specific embodiment, the training data of the training data set is input into the neural network daily measurement model for training, and after being compared with the test data, the stable neural network daily measurement model is obtained by continuously adjusting parameters. And continuously adjusting model parameters by comparing the initial output value and the real output value of the LSTM daily measurement model, thereby obtaining a stable model. The training process of the neural network weekly measurement model is similar to that of the neural network daily measurement model, the difference is that data of the neural network weekly measurement model is input, and the input historical dangerous waste processing data are the dangerous waste receiving amount, the dangerous waste disposal amount, the dangerous waste output amount and the corresponding date type of a dangerous waste enterprise which is continuously provided with a plurality of weeks before the prediction date and has the same week number as the prediction date.
In a specific embodiment, the input data are historical dangerous waste processing data of the last week and the same day of the prediction day and historical dangerous waste processing data of the last week and the same day of the prediction day, and model parameters are continuously adjusted through comparison processing between an initial output value and a real output value of the neural network weekly measurement model, so that a stable neural network weekly measurement model is obtained; and aiming at monday to sunday, 7 neural network weekly measurement models are formed by training, namely the neural network weekly measurement models respectively extract historical dangerous waste treatment data according to the situation that the neural network weekly measurement models are located on monday, tuesday, wednesday, thursday, friday, saturday or sunday, and a predicted value of the weekly measurement dangerous waste disposal quantity and a predicted value of the dangerous waste output quantity of a prediction day of the corresponding week are obtained. Therefore, after 7 neural network weekly measurement models are trained, the corresponding neural network weekly measurement model is selected according to the week number of the prediction day.
After normalization processing is carried out on hazardous waste receiving quantity, hazardous waste disposal quantity and hazardous waste output quantity in historical hazardous waste processing data, the preprocessed historical hazardous waste processing data are divided into a training data set and a testing data set, and a neural network daily measurement model and a neural network weekly measurement model are trained. In a specific embodiment, the prediction error of the neural network may be controlled within a preset range, and the preset range may be 5% to 10%.
S103, performing fusion calculation on the daily-measured dangerous waste treatment amount predicted value and the dangerous waste output amount predicted value and the weekly-measured dangerous waste treatment amount predicted value and the dangerous waste output amount predicted value respectively to obtain a predicted dangerous waste treatment amount final predicted value and a predicted dangerous waste output amount final predicted value;
in an optional embodiment, the fusion calculation of the daily measurement predicted value of the amount of hazardous waste disposal and the daily measurement predicted value of the output of hazardous waste with the weekly measurement predicted value of the amount of hazardous waste disposal and the weekly measurement predicted value of the output of hazardous waste is specifically performed, and specifically includes: carrying out fusion calculation on the predicted value of the daily measurement dangerous waste disposal quantity and the predicted value of the weekly measurement dangerous waste disposal quantity by utilizing a fusion calculation formula, and carrying out fusion calculation on the predicted value of the daily measurement dangerous waste output quantity and the predicted value of the weekly measurement dangerous waste output quantity by utilizing the fusion calculation formula, wherein the fusion calculation formula is that Y is alpha Ydi+β*YwiWherein i is 1,2, and Y isd1For daily measurement of the predicted value of the amount of the hazardous waste, Yw1For weekly measurement of the predicted value of the amount of hazardous waste disposal, Yd2For daily measurement of the output predicted value of dangerous waste, Yw2Alpha and beta are parameters for weekly testing dangerous waste output quantity predicted values, and alpha and beta values can be determined according to model training.
For the daily measurement dangerous waste treatment amount predicted value and the weekly measurement dangerous waste treatment amount predicted value, the daily measurement dangerous waste treatment amount predicted value and the weekly measurement dangerous waste treatment amount predicted value are subjected to fusion calculation by utilizing a fusion calculation formula, and Y is alpha Yd1+β*Yw1If the predicted day is Monday, Y in the calculation formula is fusedw1And 3, carrying out weekly survey on the predicted value of the hazardous waste disposal quantity on Monday, and so on. Fusion calculation formula Y ═ α × Yd2+β*Yw2In (1), the Y isw2The predicted value of weekly-measured dangerous waste disposal quantity of the predicted day obtained by the neural network weekly measurement model is Yd2The predicted value of the daily measured hazardous waste disposal quantity of the predicted day is obtained through a neural network daily measurement model. Before prediction, the fusion calculation formula also needs to be trained, namely, a neural network peripheral measurement model and a neural network daily measurement model are trained respectively, and then the fusion calculation formula Y is alpha Ydi+β*YwiTraining is performed to obtain the values of the parameters alpha and beta. After training of the neural network daily measurement model and the neural network periodic measurement model, the whole fusion calculation formula is trained, the neural network daily measurement model is similar in the training process, namely, the preprocessed historical dangerous waste processing data is divided into a training data set and a testing data set, the training data is input into a data set equation, and the values of alpha and beta are determined after the training data is compared with the testing data.
For the daily measurement dangerous waste output quantity predicted value and the weekly measurement dangerous waste output quantity predicted value, performing fusion calculation with the daily measurement dangerous waste disposal quantity predicted value and the weekly measurement dangerous waste disposal quantity predicted value, and similarly, training the whole fusion calculation formula to obtain the values of the parameters alpha and beta, which is not repeated herein.
It should be noted that the final predicted value of the predicted hazardous waste disposal amount and the final predicted value of the predicted hazardous waste output amount obtained in step S103 are not real predicted values, and the real predicted values are obtained by inverse operation of normalizing the final predicted value of the predicted hazardous waste disposal amount and the final predicted value of the predicted hazardous waste output amount.
And S104, determining whether to perform early warning or not according to the final predicted value of the hazardous waste disposal quantity and the final predicted value of the predicted hazardous waste output quantity.
In an optional embodiment, determining whether to perform early warning according to the final predicted value of the hazardous waste disposal quantity and the final predicted value of the predicted hazardous waste output quantity specifically includes: and if the ratio of the final predicted value of the hazardous waste disposal quantity to the final predicted value of the predicted hazardous waste output quantity is greater than a set threshold value, alarming, otherwise, not alarming.
In specific implementation, the set threshold value can be set to be 1, the ratio of the final predicted value of the predicted hazardous waste disposal quantity to the final predicted value of the predicted hazardous waste output quantity on the predicted day is greater than 1, early warning is carried out, and otherwise, early warning is not carried out.
In a specific embodiment, an indicator lamp is arranged, when the ratio of the predicted final predicted value of the amount of hazardous waste disposal to the predicted final predicted value of the amount of hazardous waste output is smaller than or equal to a first set threshold value, no early warning is performed, the indicator lamp performs green early warning, when the ratio of the predicted final predicted value of the amount of hazardous waste disposal to the predicted final predicted value of the amount of hazardous waste output is larger than the first set threshold value, the indicator lamp performs yellow early warning to remind workers of shortage of enterprises handling hazardous waste disposal, related departments need to be reminded of emergency treatment of the amount of hazardous waste disposal, when the ratio of the predicted final predicted value of the amount of hazardous waste disposal to the predicted final predicted value of the amount of hazardous waste output is larger than a second set threshold value, the indicator lamp performs red early warning, the emergency treatment of the amount of hazardous waste disposal needs to be performed immediately, and redundant hazardous waste is processed timely.
According to the method for early warning of the hazardous waste disposal capacity provided by the embodiment of the invention, first preset historical hazardous waste treatment data is input into a neural network daily measurement model to obtain a daily measurement hazardous waste disposal capacity predicted value and a daily measurement hazardous waste output capacity predicted value of a prediction day, wherein the neural network daily measurement model is a neural network model for predicting daily hazardous waste disposal capacity at intervals of 1 day; inputting second preset historical hazardous waste treatment data to a neural network weekly measuring model according to the day of week of the prediction, and obtaining a weekly measurement hazardous waste disposal quantity prediction value and a weekly measurement hazardous waste output quantity prediction value of the prediction day, wherein the neural network weekly measuring model is a neural network model for predicting the weekly same-day hazardous waste disposal quantity at intervals of 7 days; respectively carrying out fusion calculation on the predicted value of the daily-measured hazardous waste disposal quantity and the predicted value of the weekly-measured hazardous waste disposal quantity and the predicted value of the daily-measured hazardous waste output quantity and the predicted value of the weekly-measured hazardous waste output quantity to obtain a final predicted value of the hazardous waste disposal quantity and a final predicted value of the predicted hazardous waste output quantity; determining whether to perform early warning or not according to the final predicted value of the hazardous waste disposal quantity and the final predicted value of the predicted hazardous waste output quantity; through the mode, the current hazardous waste disposal quantity and the hazardous waste output quantity are predicted, and the early warning of the hazardous waste disposal capacity is realized, so that the natural ecological environment of a city is protected.
The useless processing volume of danger and the useless output of danger in the city are unset at present, therefore whether the useless output of danger in the city surpasss the useless processing quantity of danger every day of useless enterprise in the city becomes to need solving at present urgently, if the useless output of danger every day in the city surpasss the useless processing quantity of danger every day of useless enterprise in the city, will cause the useless accumulation of danger in the city, influence the air circumstance and the natural ecological environment's of city problem. According to the embodiment of the invention, data statistics and comprehensive training are carried out on the hazardous waste receiving quantity, the hazardous waste disposal quantity and the hazardous waste output quantity of hazardous waste disposal enterprises in a certain area through a neural network model, the hazardous waste disposal quantity and the hazardous waste output quantity are predicted, when the hazardous waste output quantity exceeds a standard (if the ratio of the final predicted value of the hazardous waste disposal quantity to the final predicted value of the predicted hazardous waste output quantity is greater than a set threshold), emergency treatment of hazardous waste disposal is carried out in the area, for example, a part of hazardous waste is transported to other areas with redundant disposal capacity, and the hazardous waste disposal enterprises are timely added so as to ensure that the hazardous waste output quantity cannot damage the urban ecological environment, and ensure that the hazardous waste generated in the area per month can be timely cleaned up, thereby protecting the natural ecological environment of the city.
The hazardous waste disposal capability early warning method can be constructed based on artificial intelligence, and related data is acquired and processed based on artificial intelligence technology, so that unattended artificial intelligence hazardous waste disposal capability early warning is realized. Among them, Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.
The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like.
Fig. 2 is a schematic structural diagram of a hazardous waste disposal capability early warning device according to a second embodiment of the present invention. As shown in fig. 2, the hazardous waste disposal capability early warning device 20 includes a daily measurement prediction module 21, a weekly measurement prediction module 22, a fusion prediction module 23, and an early warning module 24; the daily measurement prediction module 21 is configured to input first preset historical hazardous waste treatment data to a neural network daily measurement model to obtain a daily measurement hazardous waste treatment amount prediction value and a daily measurement hazardous waste output amount prediction value of a prediction day, where the neural network daily measurement model is a neural network model for performing daily hazardous waste treatment amount prediction at intervals of 1 day; the weekly measurement prediction module 22 is configured to input second preset historical hazardous waste treatment data to the neural network weekly measurement model according to the day of week of prediction to obtain a weekly measurement hazardous waste treatment amount prediction value and a weekly measurement hazardous waste output amount prediction value on the day of prediction, and the neural network weekly measurement model is a neural network model for predicting the weekly same day of hazardous waste treatment amount at intervals of 7 days; the fusion prediction module 23 is configured to perform fusion calculation on the daily measurement hazardous waste treatment amount predicted value and the weekly measurement hazardous waste treatment amount predicted value, and the daily measurement hazardous waste output amount predicted value and the weekly measurement hazardous waste output amount predicted value, respectively, to obtain a final hazardous waste treatment amount predicted value and a final predicted value of the predicted hazardous waste output amount; and the early warning module 24 is configured to determine whether to perform early warning according to the predicted final predicted value of the amount of the hazardous waste and the predicted final predicted value of the output amount of the hazardous waste. The first preset historical hazardous waste treatment data comprises hazardous waste receiving quantity, hazardous waste disposal quantity, hazardous waste output quantity and corresponding date types of hazardous waste enterprises which are continuously used for multiple days before a prediction date; the second preset historical dangerous waste treatment data comprises dangerous waste receiving quantity, dangerous waste disposal quantity, dangerous waste output quantity and corresponding date types of dangerous waste enterprises of which the weeks are the same as the predicted days in a plurality of continuous weeks before the predicted days, wherein the date types are one of holidays and non-holidays.
Furthermore, the dangerous waste disposal capacity early warning device further comprises a data processing module, and the data processing module is used for carrying out normalization processing on the dangerous waste receiving capacity, the dangerous waste disposal capacity and the dangerous waste output capacity before inputting first preset historical dangerous waste processing data into the neural network daily measurement model and inputting second preset historical dangerous waste processing data into the neural network weekly measurement model.
Further, the hazardous waste disposal capability early warning device also comprises a model training module, wherein the model training module is used for determining an input layer node unit vector, a hidden layer node unit vector, a feedback state vector and an output layer node vector of the neural network and constructing a neural network model; calculating the error of the neural network model according to first preset historical hazardous waste treatment data input to the neural network model, and updating the parameters of the neural network according to the error of the neural network model; and when the error of the neural network model is within a preset range, finishing the training of the neural network model to obtain the daily measurement model of the neural network. The nonlinear state space expression of the neural network model is
y(k)=g(w3l(k))
l(k)=f(w1c(k)+w2(x(k)))
c(k)=l(k-1)
Wherein y (k) represents the output level node vector, l (k) represents the hidden level node unit vector, x (k) represents the input vector, c (k) represents the feedback state vector, w3Representing the connection weight, w, of the hidden layer to the output layer2Representing the connection weight, w, of the input layer to the hidden layer1Representing the connection weights of the socket layer to the hidden layer, g (×) representing the transfer function of the output neurons, and f (×) representing the transfer function of the hidden layer neurons.
The neural network model can be an elman-based neural network model, which is a typical local regression network model and is proposed for speech processing. During specific implementation, the dangerous waste receiving quantity, the dangerous waste disposal quantity, the dangerous waste output quantity and the corresponding date type of a dangerous waste enterprise continuously for a plurality of days before the prediction date are used as the input of the elman-based neural network model, and the predicted daily dangerous waste disposal quantity and the predicted daily dangerous waste output quantity are used as the output of the elman-based neural network model.
Further, the fusion prediction module 23 is further configured to perform fusion calculation on the daily measurement dangerous waste disposal quantity predicted value and the weekly measurement dangerous waste disposal quantity predicted value by using a fusion calculation formula, and perform fusion calculation on the daily measurement dangerous waste output quantity predicted value and the weekly measurement dangerous waste output quantity predicted value by using a fusion calculation formula, where Y is α Ydi+β*YwiWherein i is 1,2, and Y isd1For daily measurement of the predicted value of the amount of the hazardous waste, Yw1For weekly measurements of the predicted value of the amount of hazardous waste disposal, Yd2For daily measurement of the output predicted value of dangerous waste, Yw2The predicted value of the output of the weekly-detected dangerous waste is obtained, and alpha and beta are parameters.
Further, the early warning module 24 is further configured to alarm when a ratio of the final predicted value of the hazardous waste disposal amount to the final predicted value of the predicted hazardous waste output amount is greater than a set threshold, and otherwise, not alarm.
Fig. 3 is a schematic structural diagram of an electronic device according to a third embodiment of the present invention. As shown in fig. 3, the electronic device 30 includes a processor 31 and a memory 32 coupled to the processor 31.
The memory 32 stores program instructions for implementing the hazardous waste disposal capability warning method of any of the above embodiments.
The processor 31 is operative to execute program instructions stored in the memory 32 for performing code testing.
The processor 31 may also be referred to as a CPU (Central Processing Unit). The processor 31 may be an integrated circuit chip having signal processing capabilities. The processor 31 may also be a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
Referring to fig. 4, fig. 4 is a schematic structural diagram of a storage medium according to a fourth embodiment of the invention. The storage medium of the embodiments of the present invention, which stores program instructions 41 capable of implementing all the methods described above, may be either non-volatile or volatile. The program instructions 41 may be stored in the storage medium in the form of a software product, and include several instructions to enable a computer device (which may be a personal computer, a server, or a network device) or a processor (processor) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a mobile hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, or terminal devices, such as a computer, a server, a mobile phone, and a tablet.
In the embodiments provided in the present invention, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, a division of modules is merely a division of logical functions, and an actual implementation may have another division, for example, a plurality of modules or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or modules, and may be in an electrical, mechanical or other form.
In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each module may exist alone physically, or two or more modules are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit. The above description is only an embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes performed by the present specification and drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
While the foregoing is directed to embodiments of the present invention, it will be understood by those skilled in the art that various changes may be made without departing from the spirit and scope of the invention.
Claims (10)
1. A dangerous waste disposal capacity early warning method is characterized by comprising the following steps:
inputting first preset historical hazardous waste treatment data to a neural network daily measurement model to obtain a daily measurement hazardous waste disposal quantity predicted value and a daily measurement hazardous waste output quantity predicted value of a prediction day, wherein the neural network daily measurement model is a neural network model for predicting daily hazardous waste disposal quantity at intervals of 1 day;
inputting second preset historical hazardous waste treatment data to a neural network weekly measuring model according to the week number of the prediction day to obtain a weekly measuring hazardous waste treatment amount prediction value and a weekly measuring hazardous waste output amount prediction value of the prediction day, wherein the neural network weekly measuring model is a neural network model for predicting weekly and daily hazardous waste treatment amounts at intervals of 7 days;
respectively carrying out fusion calculation on the predicted value of the daily-measured hazardous waste disposal quantity and the predicted value of the weekly-measured hazardous waste disposal quantity and the predicted value of the daily-measured hazardous waste output quantity and the predicted value of the weekly-measured hazardous waste output quantity to obtain a final predicted value of the hazardous waste disposal quantity and a final predicted value of the predicted hazardous waste output quantity;
and determining whether to perform early warning or not according to the final predicted value of the hazardous waste disposal quantity and the final predicted value of the predicted hazardous waste output quantity.
2. The method for early warning of hazardous waste disposal capability of claim 1, wherein the first preset historical hazardous waste treatment data comprises hazardous waste receiving amount, hazardous waste disposal amount, hazardous waste output amount and corresponding date type of a hazardous waste enterprise for a plurality of consecutive days before a prediction day; the second preset historical dangerous waste treatment data comprises dangerous waste receiving amount, dangerous waste disposal amount, dangerous waste output amount and corresponding date types of dangerous waste enterprises of which the weeks before the prediction day are the same as the week of the prediction day, wherein the date types are one of holidays and non-holidays.
3. The method for warning dangerous waste disposal capacity according to claim 2, further comprising normalizing the dangerous waste receiving capacity, the dangerous waste disposal capacity and the dangerous waste output capacity before inputting a first preset historical dangerous waste processing data into the neural network daily measurement model and inputting a second preset historical dangerous waste processing data into the neural network periodic measurement model.
4. The method for warning the hazardous waste disposal capability of claim 1, wherein the training step of the neural network daily measurement model comprises:
determining an input layer node unit vector, a hidden layer node unit vector, a feedback state vector and an output layer node vector of the neural network, and constructing a neural network model;
calculating the error of the neural network model according to first preset historical hazardous waste treatment data input to the neural network model, and updating the parameters of the neural network according to the error of the neural network model;
and when the error of the neural network model is within a preset range, finishing the training of the neural network model to obtain the daily measurement model of the neural network.
5. The method for warning hazardous waste disposal capability of claim 4, wherein the nonlinear state space expression of the neural network model is
y(k)=g(w3l(k))
l(k)=f(w1c(k)+w2(x(k)))
c(k)=l(k-1)
Wherein y (k) represents the output level node vector, l (k) represents the hidden level node unit vector, x (k) represents the input vector, c (k) represents the feedback state vector, w3Representing the connection weight, w, from the hidden layer to the output layer2Representing the connection weight, w, of the input layer to the hidden layer1Representing the connection weights of the socket layer to the hidden layer, g (×) representing the transfer function of the output neurons, and f (×) representing the transfer function of the hidden layer neurons.
6. The method for early warning of hazardous waste disposal capacity according to claim 1, wherein the fusion calculation of the predicted value of daily-measured hazardous waste disposal quantity and the predicted value of daily-measured hazardous waste output quantity with the predicted value of weekly-measured hazardous waste disposal quantity and the predicted value of weekly-measured hazardous waste output quantity respectively comprises:
carrying out fusion calculation on the predicted value of the daily measurement dangerous waste disposal quantity and the predicted value of the weekly measurement dangerous waste disposal quantity by utilizing a fusion calculation formula, and carrying out fusion calculation on the predicted value of the daily measurement dangerous waste output quantity and the predicted value of the weekly measurement dangerous waste output quantity by utilizing the fusion calculation formula, wherein the fusion calculation formula is that Y is alpha Ydi+β*YwiWherein i is 1,2, and Y isd1For daily measurement of the predicted value of the amount of the hazardous waste, Yw1For weekly measurement of the predicted value of the amount of hazardous waste disposal, Yd2For daily measurement of the output predicted value of dangerous waste, Yw2The predicted value of the output of the weekly-detected dangerous waste is obtained, and alpha and beta are parameters.
7. The method for early warning of hazardous waste disposal capacity according to claim 1, wherein whether early warning is performed is determined according to the final predicted value of the hazardous waste disposal quantity and the final predicted value of the predicted hazardous waste output quantity, and specifically comprises: and if the ratio of the final predicted value of the hazardous waste disposal quantity to the final predicted value of the predicted hazardous waste output quantity is greater than a set threshold value, alarming, otherwise, not alarming.
8. A dangerous waste disposal capacity early warning method is characterized by comprising a daily measurement prediction module, a weekly measurement prediction module, a fusion prediction module and an early warning module;
the daily measurement prediction module is used for inputting first preset historical hazardous waste treatment data to the neural network daily measurement model to obtain a daily measurement hazardous waste treatment amount prediction value and a daily measurement hazardous waste output amount prediction value of a prediction day, and the neural network daily measurement model is a neural network model for predicting daily hazardous waste treatment amounts at intervals of 1 day;
the weekly measurement prediction module is used for inputting second preset historical dangerous waste treatment data into the neural network weekly measurement model according to the day of week of prediction to obtain a weekly measurement dangerous waste treatment amount prediction value and a weekly measurement dangerous waste output amount prediction value on the day of prediction, and the neural network weekly measurement model is a neural network model for predicting the daily dangerous waste treatment amount every week at intervals of 7 days;
the fusion prediction module is used for performing fusion calculation on the daily measurement dangerous waste treatment amount predicted value and the daily measurement dangerous waste output predicted value and the weekly measurement dangerous waste treatment amount predicted value and the weekly measurement dangerous waste output predicted value respectively to obtain a predicted dangerous waste treatment amount final predicted value and a predicted dangerous waste output final predicted value;
and the early warning module is used for determining whether to carry out early warning according to the final predicted value of the predicted hazardous waste disposal quantity and the final predicted value of the predicted hazardous waste output quantity.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the hazardous waste disposal capability warning method of any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium storing a computer program, wherein the computer program is executed by a processor to implement the hazardous waste disposal capability warning method according to any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210241399.7A CN114638412B (en) | 2022-03-11 | Dangerous waste disposal capacity early warning method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210241399.7A CN114638412B (en) | 2022-03-11 | Dangerous waste disposal capacity early warning method and device, electronic equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114638412A true CN114638412A (en) | 2022-06-17 |
CN114638412B CN114638412B (en) | 2024-07-02 |
Family
ID=
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117557041A (en) * | 2023-11-17 | 2024-02-13 | 北京华通信联科技有限公司 | Edge calculation-based off-line automatic control method for dangerous waste transfer |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2013080304A (en) * | 2011-10-03 | 2013-05-02 | Hitachi-Ge Nuclear Energy Ltd | Danger prediction supporting system and danger prediction supporting method |
US20140052422A1 (en) * | 2011-02-14 | 2014-02-20 | Jinquan Wan | Method and system for wastewater treatment based on dissolved oxygen control by fuzzy neural network |
CN104504297A (en) * | 2015-01-21 | 2015-04-08 | 甘肃百合物联科技信息有限公司 | Method for using neural network to forecast hypertension |
CN113033092A (en) * | 2021-03-24 | 2021-06-25 | 石化盈科信息技术有限责任公司 | Sewage treatment data processing method and device, computer equipment and storage medium |
CN113516416A (en) * | 2021-08-11 | 2021-10-19 | 广西壮族自治区环境应急与事故调查中心 | Method, device, equipment and medium for evaluating cement kiln waste disposal complete cycle |
WO2022048168A1 (en) * | 2020-09-03 | 2022-03-10 | 上海上讯信息技术股份有限公司 | Training method and device for failure prediction neural network model |
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140052422A1 (en) * | 2011-02-14 | 2014-02-20 | Jinquan Wan | Method and system for wastewater treatment based on dissolved oxygen control by fuzzy neural network |
JP2013080304A (en) * | 2011-10-03 | 2013-05-02 | Hitachi-Ge Nuclear Energy Ltd | Danger prediction supporting system and danger prediction supporting method |
CN104504297A (en) * | 2015-01-21 | 2015-04-08 | 甘肃百合物联科技信息有限公司 | Method for using neural network to forecast hypertension |
WO2022048168A1 (en) * | 2020-09-03 | 2022-03-10 | 上海上讯信息技术股份有限公司 | Training method and device for failure prediction neural network model |
CN113033092A (en) * | 2021-03-24 | 2021-06-25 | 石化盈科信息技术有限责任公司 | Sewage treatment data processing method and device, computer equipment and storage medium |
CN113516416A (en) * | 2021-08-11 | 2021-10-19 | 广西壮族自治区环境应急与事故调查中心 | Method, device, equipment and medium for evaluating cement kiln waste disposal complete cycle |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117557041A (en) * | 2023-11-17 | 2024-02-13 | 北京华通信联科技有限公司 | Edge calculation-based off-line automatic control method for dangerous waste transfer |
CN117557041B (en) * | 2023-11-17 | 2024-06-11 | 北京华通信联科技有限公司 | Edge calculation-based off-line automatic control method for dangerous waste transfer |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110298560B (en) | Method and device for evaluating atmospheric pollution emission control effect and storage medium | |
Russo et al. | Neural network forecast of daily pollution concentration using optimal meteorological data at synoptic and local scales | |
CN111768038B (en) | Pollutant monitoring method and device, terminal equipment and storage medium | |
Krishnamurthy et al. | Propagation of uncertainty in transportation land use models: Investigation of DRAM-EMPAL and UTPP predictions in Austin, Texas | |
Ba-Alawi et al. | Intelligent sensor validation for sustainable influent quality monitoring in wastewater treatment plants using stacked denoising autoencoders | |
CN110533239B (en) | Smart city air quality high-precision measurement method | |
CN114565196B (en) | Multi-event trend prejudging method, device, equipment and medium based on government affair hotline | |
CN110210774B (en) | Landslide risk evaluation method and system | |
CN116681292A (en) | Petrochemical harbor security risk analysis and responsibility division method based on deep learning | |
Nakhaei et al. | Enhancing community resilience in arid regions: A smart framework for flash flood risk assessment | |
Jia et al. | A situation assessment method for rock burst based on multi-agent information fusion | |
CN111428405B (en) | Fine particulate matter concentration simulation method and device, storage medium and electronic equipment | |
CN114638412A (en) | Hazardous waste disposal capacity early warning method and device, electronic equipment and storage medium | |
CN114638412B (en) | Dangerous waste disposal capacity early warning method and device, electronic equipment and storage medium | |
CN116090710B (en) | Management method, system, electronic equipment and medium for enterprise pollution discharge permission | |
CN116384775A (en) | Management method, system and storage medium of pollution site monitoring equipment | |
CN115839344A (en) | Wear monitoring method, device, equipment and storage medium for slurry pump | |
Safari et al. | An Interval Type-2 Fuzzy LSTM Algorithm for Modeling Environmental Time-Series Prediction | |
Gill et al. | A deep neural network based context-aware smart epidemic surveillance in smart cities | |
Noor et al. | Downscaling of daily average rainfall of Kota Bharu Kelantan, Malaysia | |
CN110111022B (en) | Water pollution source evaluation method and device | |
Batterman et al. | Threshold quantity criteria for risk management programs: recommendations for toxic releases | |
Zhang et al. | Situational-aware multi-graph convolutional recurrent network (sa-mgcrn) for travel demand forecasting during wildfires | |
Lee et al. | Constructed Wetlands: prediction of performance with case-based reasoning (Part B) | |
Kunt et al. | Air pollution modelling of Konya City center by using artificial intelligence methods |
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 | ||
GR01 | Patent grant |