Risk management and control device and method based on digital water conservancy and water affairs industrial control system

Abstract

A risk control device and method based on a digital water conservancy and water affairs industrial control system belongs to the field of risk prevention and control technology. In the system, a sensor is used to detect the water quality of a reaction pool and provide the water quality information to a PLC; the PLC transmits the water quality information to a host computer after processing, and the host computer generates a dosing instruction based on the water quality information; the process operation probe is used to obtain the dosing instruction sent by the host computer and provide it to a risk control platform, and the process parameter probe is used to obtain the water quality information provided by the PLC, and then provide it to the risk control platform; the risk control platform is used to verify the dosing instruction, track the abnormal instruction for the dosing instruction that has been verified to be wrong, and transmit the verified correct dosing instruction to the PLC; the industrial control actuator performs the dosing operation according to the dosing instruction provided by the PLC to purify the water in the reaction pool. The present invention can automatically identify abnormal dosing instructions and prevent risks related to digital water conservancy and water affairs before they occur.

Description

Technical Field

[0001] The present invention relates to a risk control device and method based on a digital water conservancy and water affairs industrial control system, belonging to the technical field of risk prevention and control. Background Art

[0002] The Chinese invention patent application with publication number CN110737237A discloses a water management system, which is hierarchically constructed, including a perception layer, a network layer, and an application layer. The perception layer includes information collection or monitoring equipment set in different water scenarios; the network layer includes multiple central control room PLC control dispatchers set in different water scenarios, and the central control room PLC control dispatchers include a main controller ST20, an analog input and output controller EM AE04, and an analog input and output controller EM AE03. The network layer can receive status bit data and analog data from the perception layer; the network layer also includes network message rules based on the PLC controller. The water management systems disclosed in the invention patent application are connected on the Internet, which makes them vulnerable to attacks. Summary of the invention

[0003] In order to overcome the shortcomings of the prior art, the object of the present invention is to provide a risk management device and method based on a digital water conservancy and water affairs industrial control system, which can automatically identify abnormal dosing instructions and prevent risks related to digital water conservancy and water affairs before they occur.

[0004] To achieve the above-mentioned purpose, the present invention provides a risk management and control device based on a digital water conservancy and water affairs industrial control system, which includes a host computer, a PLC, an industrial control actuator, a reaction tank and a sensor, wherein the sensor is used to detect the water quality of the water in the reaction tank and provide the water quality information to the PLC; the PLC transmits the water quality information to the host computer after processing, and the host computer generates a dosing instruction based on the water quality information. The risk management and control device also includes a process operation probe, a process parameter probe and a risk control platform, wherein the process operation probe is used to obtain the dosing instruction sent by the host computer. The process parameter probe is used to obtain water quality information provided by the PLC and then provide it to the risk control platform; the risk control platform is used to verify the dosing instructions and send the verified incorrect dosing instructions to the risk control platform. Track abnormal instructions and verify the correct dosing instructions Release, the host computer transmits it to PLC; the industrial control execution agency verifies the correct dosing instructions provided by PLC Perform dosing operation to purify the water in the reaction pool; the risk control platform includes a simulator and a risk prediction model, and the simulator is based on the dosing instructions u provided by the process operation probe k Generate a simulation function, and simulate the dosing of the industrial control actuator according to the simulation function. The simulation function is expressed as , The simulator simulates the water quality index obtained by adding drugs according to the simulation function at time k, and θ is the parameter of the simulation function; the risk prediction model infers that the water quality is The water quality index of water is c, c=1,…,C, all water quality indexes are divided into normal range and abnormal range, according to the dosing instruction Simulate dosing, the water quality changes from the normal range to the abnormal range, the dosing instruction is the abnormal instruction, the water quality changes from the abnormal range to the normal range, the dosing instruction is the normal instruction.

[0005] In order to achieve the above-mentioned object of the invention, the present invention also provides a risk management and control method based on a digital water conservancy and water affairs industrial control system, which comprises the following steps:

[0006] Step 1: Detect the water quality of the reaction tank through the sensor and provide the water quality information to the PLC;

[0007] Step 2: PLC processes the water quality information and transmits it to the host computer, which generates a dosing instruction based on the water quality information. ;

[0008] Step 3: Obtain the dosing instructions sent by the host computer through the process operation probe And provide it to the risk control platform; obtain the water quality information provided by PLC through the process parameter probe, and then provide it to the risk control platform;

[0009] Step 4: Verify the dosing instructions through the risk control platform, track the abnormal instructions for the dosing instructions that have been verified to be incorrect, and release the correct dosing instructions. The host computer will Send to PLC;

[0010] Step 5: The industrial control actuator performs the dosing operation according to the dosing instruction provided by the PLC to purify the water in the reaction tank;

[0011] Step 6: Use the simulator of the risk control platform to follow the dosing instructions provided by the process operation probe k Generate a simulation function, and simulate the dosing of the industrial control actuator according to the simulation function. The simulation function is expressed as , The simulator simulates the water quality index obtained by adding drugs according to the simulation function at time k, and θ is the parameter of the simulation function;

[0012] Step 7: Infer water quality through risk prediction model The water quality index of water is c, c=1,…,C, all water quality indexes are divided into normal range and abnormal range, according to the dosing instruction Simulate dosing, the water quality changes from the normal range to the abnormal range, the dosing instruction is the abnormal instruction, the water quality changes from the abnormal range to the normal range, the dosing instruction is the normal instruction.

[0013] Compared with the prior art, the risk management and control device and method based on the digital water conservancy and water affairs industrial control system provided by the present invention uses a process operation probe to obtain the dosing instructions sent by the host computer and provide them to the risk control platform, and a process parameter probe to obtain water quality information provided by the PLC, and then provide it to the risk control platform; the risk control platform is used to verify the dosing instructions, track the abnormal instructions for the dosing instructions that have been verified to be erroneous, and release the correct dosing instructions from the host computer to transmit to the PLC, so as to prevent risks related to digital water conservancy and water affairs before they occur. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 It is a block diagram of the composition of the risk management and control device based on the digital water conservancy and water affairs industrial control system provided by the present invention.

[0015] Figure 2 It is a block diagram of the composition of the risk control platform provided by the present invention. DETAILED DESCRIPTION

[0016] In order to make the technical means, creative features, objectives and effects achieved by the present invention easy to understand, the present invention is further explained below in conjunction with specific implementation methods.

[0017] In the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance.

[0018] First embodiment

[0019] Figure 1 It is a block diagram of the risk management and control device based on the digital water conservancy and water affairs industrial control system provided by the present invention, such as Figure 1 As shown, the risk management and control device based on the digital water conservancy and water affairs industrial control system provided by the present invention includes a host computer, a PLC, an industrial control actuator, a reaction pool and a sensor, wherein the sensor is used to detect the water quality of the reaction pool and provide the water quality information to the PLC; the PLC transmits the water quality information to the host computer after processing, and the host computer generates a dosing instruction according to the water quality information; the risk management and control device also includes a process operation probe, a process parameter probe and a risk control platform, wherein the process operation probe is used to obtain the dosing instruction sent by the host computer and provide it to the risk control platform, and the process parameter probe is used to obtain the water quality information provided by the PLC, and then provide it to the risk control platform; the risk control platform is used to verify the dosing instruction, track the abnormal instruction for the verified erroneous dosing instruction, verify the correct dosing instruction and release it, and the host computer does not issue the dosing instruction The system is transmitted to the PLC; the industrial control actuator performs the dosing operation according to the dosing instruction provided by the PLC to purify the water in the reaction tank.

[0020] In the first embodiment of the present invention, a process operation probe is used to obtain the dosing instructions sent by the host computer, a process parameter probe is used to obtain water quality information provided by the PLC, and a risk control platform is used to verify the dosing instructions. The dosing instructions that have been verified to be erroneous are tracked as abnormal instructions, and the correct dosing instructions are released and transmitted by the host computer to the PL, so as to prevent risks related to digital water conservancy and water services before they occur.

[0021] Figure 2 It is a block diagram of the composition of the risk control platform provided by the present invention, such as Figure 2 As shown, the risk control platform includes a simulator, which is based on the dosing instructions u provided by the process operation probe. k Generate a simulation function, and simulate the dosing of the industrial control actuator according to the simulation function. The simulation function is expressed as , The simulator simulates the water quality index obtained by adding medicine according to the simulation function at time k, and θ is the parameter of the simulation function.

[0022] In the present invention, the simulator is based on the dosing instruction u k Generating a simulation function includes the following process:

[0023] The simulator operates the dosing instructions provided by the probe according to the process And process parameter data probe provides water quality indicators Generate dosing trajectory , k=1,...,K, The industrial control actuator detects the dosing instruction at time k. Water quality indicators after adding medicine;

[0024] Get water quality indicators based on simulation functions: , k=1,...,K;

[0025] The error is calculated by the following formula: ,k=1,...,K;

[0026] Update the parameters of the simulation function by:

[0027] ,

[0028] In the formula, is the learning coefficient, is the discount factor; is the evaluation function, are the parameters of the evaluation function.

[0029] The flexibility and applicability of the simulator obtained by the present invention through the above technical solution are improved, and the efficiency is high.

[0030] The risk control platform also includes a risk prediction model; the simulator obtains water quality based on the simulation function: ; The risk prediction model infers that the water quality is The water quality index of water is c, c=1,…,C, all water quality indexes are divided into normal range and abnormal range, according to the dosing instruction Simulate dosing, the water quality index changes from the normal range to the abnormal range, the dosing instruction is the abnormal instruction, the water quality index changes from the abnormal range to the normal range, the dosing instruction is the normal instruction.

[0031] In the present invention, the risk prediction model is based on the Bayesian network Trained, is the parameter of the Bayesian network. Training the Bayesian network into a risk prediction model includes the following steps:

[0032] S1-1: Obtain a training data set, wherein the training data set includes a labeled training data set and unlabeled training dataset ;

[0033] S1-2: Setting the loss function for:

[0034] ,

[0035] In the formula, For the Bayesian network with labeled data Predicted water quality indicators; For labeled data Labels; For unlabeled data Pseudo labels of For the Bayesian network with labeled data Predicted water quality indicators, To dynamically adjust parameters;

[0036] S1-3: Loss through labeling Update Bayesian Network Parameters:

[0037] ,

[0038] In the formula, is the learning rate, For The gradient of

[0039] S1-4: Determine the loss function Is it the minimum? If the loss function If the loss function does not reach the minimum, return to S1-1. When it reaches the minimum, the training is terminated to obtain the risk prediction model.

[0040] The present invention trains the Bayesian network into a risk prediction model through the above technical solution.

[0041] In the first embodiment of the present invention, the tracing of abnormal instructions includes:

[0042] S2-1: An undirected knowledge graph is constructed with multiple existing malware that send abnormal instructions as entities and the relationships between existing malware as edges. Malware refers to computer software that can perform malicious behaviors. Each node in the undirected knowledge graph stores two attributes, one is its most similar node, recorded as the MSTo attribute, and the other is the set of nodes with it as the most similar node, recorded as the MSFrom attribute;

[0043] S2-2: Cluster the existing malware according to the undirected knowledge graph and divide it into multiple clusters to obtain the malware cluster set CL = [CL1, ..., CL u , …, CL U ],A malware cluster is a malware family, and malware in the same family has some commonalities in terms of code structure, functional implementation, etc.;

[0044] S2-3: Calculate the newly discovered malware S NEW With each cluster CL in the existing cluster set CL u If the repulsion of u If they are mutually exclusive, execute S2-5; if there are non-exclusive clusters, the non-exclusive cluster set is recorded as CL ~ =[CL1,…, CL q , …, CL Q ], then calculate the newly discovered malware S NEW The similarity Sim(S NEW ,CL q );

[0045] S2-4: If Sim(S NEW ,CL q ) is less than the threshold, execute S2-5; if Sim(S NEW ,CL q ) is greater than or equal to the threshold, the newly discovered malware S NEW Place in Sim(S NEW ,CL q ) in the largest cluster;

[0046] S2-5: According to the newly discovered malware S NEW Create a new cluster CL NEW , and cluster CL NEW Join the cluster set CL;

[0047] S2-6: Repeat S2-3, S2-4, and S2-5 until all newly discovered malware S NEW Clustering is complete.

[0048] In the first embodiment, the newly discovered malware S is calculated. NEW With each cluster CL in the existing cluster set CL u The repulsion of the newly discovered malware S NEW With malwareS qw Generate their subsequences respectively. If all subsequences are different, then the malware S NEW With malwareS qw Repel each other.

[0049] In the first embodiment, the newly discovered malware S NEW The similarity Sim(S NEW ,CL q ) is obtained by the following steps:

[0050] S3-1: Newly discovered malware S NEW Decompile to obtain an assembly file, extract strings and reference addresses of strings from the assembly file, for example, by using binary analysis tools such as ida and Ghidra to decompile malware to obtain an assembly file, extract strings and reference addresses of strings from the assembly file, such as " / proc / cpuinfo" and "0040a45c";

[0051] S3-2: composing a sequence of the extracted character strings and the reference addresses of the character strings; and sorting the sequence according to the reference addresses of the character strings to generate an ascending sequence of character strings;

[0052] S3-3: Calculate the newly discovered malware S by the following formula NEW With each non-exclusive cluster CL in the set of non-exclusive clusters q Malware in S qw SimilaritySim(S NEW ,CL q ):

[0053] ,

[0054] In the formula, S NEWRepresents an increasing sequence of strings extracted from newly discovered malware; S qw Indicates CL q Incremental sequence of strings extracted from the wth malware in the cluster; LCS(S NEW ,S qw ) indicates S NEW With S qw The longest common subsequence length; Sim(S NEW ,S qw ) ranges from [0,1]. The larger the value, the higher the similarity between the ascending sequences.

[0055] S3-4: Get the newly discovered malware S NEW With each non-exclusive cluster CL in the set of non-exclusive clusters k S qw The malware with the greatest similarity is taken as malware S NEW The similarity Sim(S NEW ,CL q );Length of S qw For the newly discovered malware S NEW The longest subsequence length of the increasing sequence; Lengthof S qw For malware S qw The longest subsequence length of an increasing sequence.

[0056] The present invention can track malware that issues abnormal instructions through the above technical solution with very little computing power overhead.

[0057] Second embodiment

[0058] The second embodiment of the present invention only describes the contents that are different from the first embodiment, and the same contents will not be described repeatedly.

[0059] The risk management method based on the digital water conservancy and water industry control system provided in the second embodiment of the present invention comprises the following steps:

[0060] Step 1: Detect the water quality in the reaction tank through the sensor and provide the water quality information to the PLC;

[0061] Step 2: PLC processes the water quality information and transmits it to the host computer, which generates a dosing instruction based on the water quality information. ;

[0062] Step 3: Obtain the dosing instructions sent by the host computer through the process operation probe And provide it to the risk control platform; obtain the water quality information provided by PLC through the process parameter probe, and then provide it to the risk control platform;

[0063] Step 4: Instructions on dosing via the risk control platform Verify and remove the incorrect dosing instructions Track abnormal instructions and verify the correct dosing instructions Release, the host computer will add medicine instruction Send to PLC;

[0064] Step 5: The industrial control actuator performs the dosing operation according to the dosing instruction provided by the PLC to purify the water in the reaction tank.

[0065] The risk management and control method based on the digital water conservancy and water affairs industrial control system provided by the present invention also includes the following steps:

[0066] Step 6: Use the simulator of the risk control platform to follow the dosing instructions provided by the process operation probe k Generate a simulation function, and simulate the dosing of the industrial control actuator according to the simulation function. The simulation function is expressed as , The simulator simulates the water quality index obtained by adding medicine according to the simulation function at time k, and θ is the parameter of the simulation function.

[0067] The risk management method based on the digital water conservancy and water affairs industrial control system provided by the present invention also includes the following steps:

[0068] Step 7: Infer water quality through risk prediction model The water quality index of water is c, c=1,…,C, all water quality indexes are divided into normal range and abnormal range, according to the dosing instruction Simulate dosing, water quality changes from normal range to abnormal range, dosing instructions It is an abnormal instruction. The water quality changes from the abnormal range to the normal range. The dosing instruction It is a normal instruction.

[0069] The beneficial effects of the second embodiment of the present invention are the same as those of the first embodiment, and will not be described again here.

[0070] The present invention also provides a system, which includes a storage medium and one or more processors, wherein the storage medium stores a computer program, and the computer program is called by the one or more processors to implement the above method.

[0071] The present invention also provides a computer program product, which utilizes a computer language to compile the above method into a computer program that is called and executed by one or more processors.

[0072] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A risk management and control device based on a digital water conservancy and water affairs industrial control system, which includes a host computer, a PLC, an industrial control actuator, a reaction pool and a sensor, wherein: The sensor is used to detect the water quality of the water in the reaction tank and provide the water quality information to the PLC; the PLC transmits the water quality information to the host computer after processing, and the host computer generates a dosing instruction according to the water quality information. It is characterized in that it also includes a process operation probe, a process parameter probe and a risk control platform, wherein the process operation probe is used to obtain the dosing instruction sent by the host computer The process parameter probe is used to obtain water quality information provided by the PLC and then provide it to the risk control platform; the risk control platform is used to verify the dosing instructions and send the verified incorrect dosing instructions to the risk control platform. Track abnormal instructions and verify the correct dosing instructions Release, the host computer will add medicine instruction Transmit to PLC; the industrial control execution agency verifies the correct dosing instructions according to the PLC Perform dosing operation to purify the water in the reaction pool; the risk control platform includes a simulator and a risk prediction model, and the simulator is based on the dosing instructions u provided by the process operation probe k Generate a simulation function, simulate the dosing of the industrial control actuator according to the simulation function, and simulate the water quality obtained by dosing at time k according to the simulation function: , θ is the parameter of the simulation function; the risk prediction model infers that the water quality is The water quality index of water is c, c=1,…,C, all water quality indexes are divided into normal range and abnormal range, according to the dosing instruction Simulate dosing, the water quality index changes from the normal range to the abnormal range, the dosing instruction is the abnormal instruction, the water quality index changes from the abnormal range to the normal range, the dosing instruction is the normal instruction.

2. The risk management and control device based on the digital water conservancy and water affairs industrial control system according to claim 1 is characterized in that: The simulator follows the dosing instruction u k Generating a simulation function includes the following process: The simulator operates the dosing instructions provided by the process probe Water quality and process parameter data provided by the probe Generate dosing trajectory , k=1,...,K, The industrial control actuator detects the dosing instruction at time k. Water quality after dosing; Get the water quality at time k according to the simulation function: ,k=1,...,K; The error is calculated by the following formula: ,k=1,...,K; Update the parameters of the simulation function by: , In the formula, is the learning coefficient, is the discount factor; is the evaluation function, are the parameters of the evaluation function.

3. The risk management and control device based on the digital water conservancy and water affairs industrial control system according to claim 2 is characterized in that: Risk prediction model via Bayesian network Trained, is the parameter of the Bayesian network. Training the Bayesian network into a risk prediction model includes the following steps: S1-1: Obtain a training data set, wherein the training data set includes a labeled training data set and unlabeled training dataset ; S1-2: Setting the loss function for: ， In the formula, For the Bayesian network with labeled data Predicted water quality indicators; For labeled data Labels; For unlabeled data Pseudo labels of For Bayesian network to unlabeled data Predicted water quality indicators, To dynamically adjust parameters; S1-3: Loss through labeling Update Bayesian Network Parameters: ， In the formula, is the learning rate, For The gradient of S1-4: Determine the loss function Is it the minimum? If the loss function If the loss function does not reach the minimum, return to S1-1. When it reaches the minimum, the training is terminated to obtain the risk prediction model.

4. A risk management and control method based on a digital water conservancy and water industry control system, comprising the following steps: Step 1: Detect the water quality of the reaction tank through the sensor and provide the water quality information to the PLC; Step 2: PLC processes the water quality information and transmits it to the host computer, which generates a dosing instruction based on the water quality information. ; Step 3: Obtain the dosing instructions sent by the host computer through the process operation probe And provide it to the risk control platform; obtain water quality information provided by PLC through process parameter probe, and then provide it to the risk control platform; Step 4: Verify the dosing instructions through the risk control platform, track the abnormal instructions for the dosing instructions that have been verified to be incorrect, and release the correct dosing instructions. The host computer will Send to PLC; Step 5: The industrial control actuator performs the dosing operation according to the dosing instruction provided by the PLC to purify the water in the reaction tank; Step 6: Use the simulator of the risk control platform to follow the dosing instructions provided by the process operation probe k Generate a simulation function, simulate the dosing of the industrial control actuator according to the simulation function, and simulate the water quality obtained by dosing at time k according to the simulation function: , θ is the parameter of the simulation function; Step 7: Infer water quality through risk prediction model The water quality index of water is c, c=1,…,C, all water quality indexes are divided into normal range and abnormal range, according to the dosing instruction Simulate dosing, the water quality changes from the normal range to the abnormal range, the dosing instruction is the abnormal instruction, the water quality changes from the abnormal range to the normal range, the dosing instruction is the normal instruction.

5. The risk management and control method based on digital water conservancy and water affairs industrial control system according to claim 4 is characterized in that: The simulator follows the dosing instruction u k Generating a simulation function includes the following process: The simulator operates the dosing instructions provided by the process probe Water quality and process parameter data provided by the probe Generate dosing trajectory , k=1,...,K, The industrial control actuator detects the dosing instruction at time k. Water quality after dosing; Get the water quality at time k based on the simulation function data: , k=1,...,K; The error is calculated by the following formula: ,k=1,...,K; Update the parameters of the simulation function by: ， In the formula, is the learning coefficient, is the discount factor; is the evaluation function, are the parameters of the evaluation function.

6. The risk management and control method based on digital water conservancy and water affairs industrial control system according to claim 5 is characterized in that: Risk prediction model via Bayesian network Trained, is the parameter of the Bayesian network. Training the Bayesian network into a risk prediction model includes the following steps: S1-1: Obtain a training data set, wherein the training data set includes a labeled training data set and unlabeled training dataset ; S1-2: Setting the loss function for: ， In the formula, For the Bayesian network with labeled data Predicted water quality indicators; For labeled data Labels; For unlabeled data Pseudo labels of For Bayesian network to unlabeled data Predicted water quality indicators, To dynamically adjust parameters; S1-3: Loss through labeling Update Bayesian Network Parameters: ， In the formula, is the learning rate, For The gradient of S1-4: Determine the loss function Is it the minimum? If the loss function If the loss function does not reach the minimum, return to S1-1. When it reaches the minimum, the training is terminated to obtain the risk prediction model.

Images