Search

CN-122018414-A - Water service industry control risk prediction system based on intelligent management

CN122018414ACN 122018414 ACN122018414 ACN 122018414ACN-122018414-A

Abstract

The invention discloses a water service industrial control risk prediction system based on intelligent management, which relates to the technical field of industrial control system safety and comprises a data acquisition module, a virtual flow back calculation module, a trust residual analysis module, a cavitation state diagnosis module, a cross-domain joint reasoning module and a control system, wherein the data acquisition module acquires bottom physical operation data and process monitoring data, the virtual flow back calculation module is used for back calculating a virtual flow standard based on electric power of a motor, the trust residual analysis module is used for calculating dynamic residual and change rate between network flow and the virtual flow standard, the cavitation state diagnosis module is used for generating an acousto-electro-mechanical coupling cavitation index by combining inlet pressure, the virtual flow and volute acoustic characteristics, the cross-domain joint reasoning module is used for judging data tampering risk and triggering first response when the residual change rate is positively correlated with dosing frequency, and judging physical induced cavitation risk and triggering second response when the cavitation index is out of limit and has a water inlet instruction or flow dip.

Inventors

  • HU RONGHUA

Assignees

  • 天时地理(深圳)智能科技有限公司

Dates

Publication Date
20260512
Application Date
20260410

Claims (10)

  1. 1. Water-service industry control risk prediction system based on intelligent management, characterized by comprising: The data acquisition module is used for acquiring bottom layer physical operation data of the water pump unit, process monitoring data and control instructions in an industrial control network, wherein the bottom layer physical operation data comprise motor input electric power, water pump inlet pressure and volute acoustic emission signals, and the process monitoring data comprise flow count values read by the network; the virtual flow back calculation module is used for back calculating physical real flow flowing through the water pump based on the energy conservation relation according to the input electric power of the motor and a preset water pump characteristic curve, and taking the physical real flow as a virtual flow reference; The trust residual analysis module is used for calculating a dynamic residual between the flow count value read by the network and the virtual flow reference and extracting the change rate of the dynamic residual along with time; The cavitation state diagnosis module is used for calculating the effective cavitation allowance of the device according to the inlet pressure of the water pump and the virtual flow reference, and coupling the effective cavitation allowance of the device with the high-frequency band energy characteristic of the volute acoustic emission signal to generate an acousto-optic coupling cavitation index for representing the severity of cavitation; The cross-domain joint reasoning module is used for executing joint reasoning based on the change rate of the dynamic residual error, the dosing frequency in the process monitoring data, the acousto-optic-electric coupling cavitation index and the control instruction: If the change rate of the dynamic residual meets a preset abrupt change threshold condition and the dosing frequency is positively correlated with the flow count value, judging that the risk of data tampering exists and triggering a first safety response; and if the cavitation index of the acoustic-electromechanical coupling exceeds a preset safety threshold value and a control instruction for reducing the water inflow of the water pump exists or the virtual flow reference suddenly drops, judging that the cavitation risk is physically induced and triggering a second safety response.
  2. 2. The intelligent management-based water service industrial control risk prediction system according to claim 1, wherein the virtual flow back calculation module back calculates the physical real flow flowing through the water pump based on the energy conservation relation according to the motor input electric power and a preset water pump characteristic curve, and comprises: Converting the input electric power of the motor into water pump shaft power according to preset motor transmission efficiency; obtaining a polynomial characteristic curve model between pre-calibrated water pump shaft power and flow; Substituting the water pump shaft power into the polynomial characteristic curve model, and obtaining a real root which is compliant in physical sense by solving a polynomial equation to serve as the virtual flow reference.
  3. 3. The intelligent management-based water service industrial control risk prediction system according to claim 1, wherein the trust residual analysis module calculates a dynamic residual between the network-read flow count value and the virtual flow reference, and extracts a rate of change of the dynamic residual over time, comprising: calculating the difference value between the flowmeter value and the virtual flow reference as a dynamic residual error in a preset time window; performing time derivation processing on the dynamic residual error to obtain a time derivative sequence of the dynamic residual error; and carrying out smoothing filtering treatment on the time derivative sequence, and taking the filtered result as the change rate of the dynamic residual error along with time.
  4. 4. The intelligent management-based water service industrial control risk prediction system of claim 1, wherein the cavitation status diagnostic module calculates an effective cavitation margin from the pump inlet pressure and the virtual flow reference, comprising: Obtaining saturated vapor pressure, treatment medium density and water pump inlet sectional area under the current water temperature; Calculating a pressure difference value between the inlet pressure of the water pump and the saturated vapor pressure, and converting the pressure difference value into a pressure water head based on the density of the treatment medium and the gravity acceleration; Calculating an inlet flow rate according to the virtual flow reference and the inlet sectional area of the water pump, and converting the inlet flow rate into a kinetic energy water head; and adding the pressure water head and the kinetic energy water head to obtain the effective cavitation allowance of the device.
  5. 5. The intelligent management-based water service industry control risk prediction system of claim 4, wherein the cavitation status diagnostic module couples the effective cavitation margin of the device with the high-band energy characteristics of the volute acoustic emission signal to generate an acousto-optic coupling cavitation index that characterizes cavitation severity, comprising: Acquiring acoustic emission baseline energy under a normal cavitation-free working condition, and calculating the logarithmic ratio of the high-frequency band energy characteristic of the volute acoustic emission signal relative to the acoustic emission baseline energy to be used as an acoustic mutation characteristic; acquiring a necessary cavitation allowance of a water pump, calculating a difference value between the necessary cavitation allowance and an effective cavitation allowance of the device, and extracting a non-negative part of the difference value as a hydrodynamic boundary feature; And based on a preset weight coefficient, performing weighted fusion processing on the acoustic abrupt change feature and the fluid dynamic boundary feature to obtain the acousto-optic coupling cavitation index.
  6. 6. The smart management-based water service industrial control risk prediction system of claim 1, wherein the first safety response comprises: Generating and sending a dosing interlocking cutting-off instruction to a corresponding dosing pump control unit; recording and reporting a data tampering attack log containing the association relation between the dynamic residual error change rate and the dosing frequency; And forcedly switching the flow control reference of the system from the flowmeter value read by the network to the virtual flow reference.
  7. 7. The smart management-based water service industrial control risk prediction system of claim 1, wherein the second safety response comprises: generating and sending a gate safety reset instruction to a water inlet gate control unit so as to increase the water inlet flow of the water pump; recording and reporting a physical induction attack log containing an acousto-optic-electric coupling cavitation index and a control instruction sequence; and triggering an emergency frequency-reducing and running-down mode of the water pump unit.
  8. 8. The intelligent management-based water service industrial control risk prediction system according to claim 1, wherein the data acquisition module acquires the bottom physical operation data of the water pump unit, and comprises: collecting the input electric power of the motor through a high-frequency current transformer with external hard wire; Collecting the pressure of the inlet of the water pump through a pressure transmitter arranged at the inlet of the water pump; and acquiring the volute acoustic emission signal through an acoustic sensor attached to the surface of the water pump volute.
  9. 9. The intelligent management-based water service industry control risk prediction system according to claim 1, further comprising: And the dynamic threshold updating module is used for adaptively updating the preset abrupt threshold condition and the preset safety threshold based on the statistical characteristics of the historical normal operation data period so as to compensate the baseline drift of the water pump unit caused by long-term mechanical abrasion.
  10. 10. A water service industry control risk prediction method based on intelligent management, characterized in that based on the water service industry control risk prediction system based on intelligent management as claimed in any one of claims 1-9, the following steps are performed: Acquiring bottom layer physical operation data of a water pump unit, process monitoring data and control instructions in an industrial control network, wherein the bottom layer physical operation data comprise motor input electric power, water pump inlet pressure and volute acoustic emission signals, and the process monitoring data comprise flow count values read by the network; According to the input electric power of the motor and a preset water pump characteristic curve, reversely calculating physical real flow flowing through the water pump based on an energy conservation relation, and taking the physical real flow as a virtual flow reference; Calculating a dynamic residual error between the flow count value read by the network and the virtual flow reference, and extracting the change rate of the dynamic residual error along with time; Calculating the effective cavitation allowance of the device according to the inlet pressure of the water pump and the virtual flow reference, and coupling the effective cavitation allowance of the device with the high-frequency band energy characteristic of the volute acoustic emission signal to generate an acousto-optic coupling cavitation index representing the severity of cavitation; performing joint reasoning based on the rate of change of the dynamic residual, the dosing frequency in the process monitoring data, the acousto-optic coupling cavitation index, and the control instructions: If the change rate of the dynamic residual meets a preset abrupt change threshold condition and the dosing frequency is positively correlated with the flow count value, judging that the risk of data tampering exists and triggering a first safety response; and if the cavitation index of the acoustic-electromechanical coupling exceeds a preset safety threshold value and a control instruction for reducing the water inflow of the water pump exists or the virtual flow reference suddenly drops, judging that the cavitation risk is physically induced and triggering a second safety response.

Description

Water service industry control risk prediction system based on intelligent management Technical Field The invention relates to the technical field of industrial control system safety, in particular to a water service industrial control risk prediction system based on intelligent management. Background The intelligent management-based water service industrial control risk prediction system is mainly applied to the key infrastructure fields of urban water supply, sewage treatment and the like, and remote scheduling and safety monitoring of core process equipment such as a water pump unit, a dosing system, a pipe network gate and the like are realized through integrated sensor monitoring, automatic control and data analysis technologies. The existing industrial control safety protection system generally adopts a firewall at a network side to intercept or detect abnormality based on an information protocol, and the design thought is to judge the system state by depending on the integrity of a network layer flow message. However, under the specific scene of being subjected to deep hidden attack, a hacker can synchronously tamper a physical operation instruction issued by an upper computer (such as cavitation induced by a micro-closed water inlet gate) and false monitoring data fed back by a sensor (such as excessive addition induced by fake large flow), and the characteristic of 'instruction-feedback' synchronous spoofing enables the prior art to fail to identify the physical damage and biochemical risk covered by malicious intent due to the lack of cross checking of the physical authenticity of a bottom layer, so that the system is damaged by equipment or exceeds the standard of water quality under the condition that the logic of a data message appears normal. Therefore, a water service industrial control risk prediction system based on intelligent management is provided. Disclosure of Invention Aiming at the defects existing in the prior art, the invention provides an intelligent management water service industrial control risk prediction system. In order to achieve the above object, the technical scheme of the present invention is as follows: according to one aspect of the present application, there is provided a water service industrial control risk prediction system based on intelligent management, comprising: The data acquisition module is used for acquiring bottom layer physical operation data of the water pump unit, process monitoring data and control instructions in an industrial control network, wherein the bottom layer physical operation data comprise motor input electric power, water pump inlet pressure and volute acoustic emission signals, and the process monitoring data comprise flow count values read by the network; The virtual flow back calculation module is used for back calculating physical real flow flowing through the water pump based on the energy conservation relation according to the input electric power of the motor and a preset water pump characteristic curve, and taking the physical real flow as a virtual flow reference; the trust residual analysis module is used for calculating dynamic residual between the flowmeter value read by the network and the virtual flow reference and extracting the change rate of the dynamic residual along with time; The cavitation state diagnosis module is used for calculating the effective cavitation allowance of the device according to the inlet pressure of the water pump and the virtual flow reference, and coupling the effective cavitation allowance of the device with the high-frequency band energy characteristic of the volute acoustic emission signal to generate an acousto-optic coupling cavitation index for representing the severity of cavitation; The cross-domain joint reasoning module is used for executing joint reasoning based on the change rate of the dynamic residual error, the dosing frequency in the process monitoring data, the acousto-optic-electric coupling cavitation index and the control instruction: if the change rate of the dynamic residual error meets a preset abrupt change threshold condition and the dosing frequency is positively correlated with the flow count value, judging that the risk of data tampering exists and triggering a first safety response; If the cavitation index of the acoustic-electromechanical coupling exceeds a preset safety threshold value and a control instruction for reducing the inflow of the water pump or a virtual flow reference suddenly drops, judging that the cavitation risk is physically induced and triggering a second safety response. According to another aspect of the present application, there is provided a water service industry control risk prediction method based on intelligent management, comprising: Acquiring bottom layer physical operation data of a water pump unit, process monitoring data and control instructions in an industrial control network, wherein the bottom layer physical operation data comprise