Methods for verifying the reliability of sensor information in factory processes

Abstract

One aspect of the present invention relates to a method for verifying the reliability of sensor information sensed by a sensor device associated with a plant process, particularly a water treatment process and / or a wastewater treatment process, wherein the sensor information is related to the plant process, the method comprising: receiving the sensor information by a control unit; executing a verification model by the control unit to determine expected sensor information that the sensor device should provide, wherein the verification model determines the expected sensor information based on at least one other piece of information that is related to the plant process and has a relation to the sensor information; comparing the expected sensor information with the received sensor information; and outputting a verification signal by the control unit when it is determined that the sensor information deviates from the expected sensor information.

Description

Technical Field

[0001] The present invention relates to a method for verifying the reliability of sensor information sensed by sensor devices associated with a factory process, and a control unit for controlling a factory process. Background Technology

[0002] It is known to control plant processes, such as water treatment and / or wastewater treatment processes operating in a water treatment plant, based on sensor information provided by one or more sensor devices. The sensor information may be related to parameters of the plant process and / or stages of the plant process (e.g., nitrification and / or aeration stages). Specifically, based on the sensor information, a control unit for controlling the plant process can determine (e.g., calculate) specific process parameters and / or control activities for controlling the plant process. That is, the sensor devices and / or sensor information may be part of a feedback loop and / or feedforward strategy for controlling the plant process, and the sensor information is preferably provided continuously to the control unit, but may also be provided discontinuously, for example, based on laboratory results. For example, a sensor device may provide sensor information about the phosphorus concentration in (waste)water, and the control unit may determine, based on said sensor information, the dosage of a chemical (here, a precipitant) to be applied in the plant process to meet a specific phosphorus concentration. Further examples of sensor devices involve sensor devices that provide sensor information about ammonia, nitrate, oxygen, residual chlorine, concentration, pH, and conductivity.

[0003] To ensure optimal operation of the plant process, the uptime, reliability, and quality of sensor information are crucial. In other words, sensor information that deviates from the actual parameters of the plant process it refers to may lead to insufficient control of the plant process by the control unit. This could result in failure to meet certain quality requirements of the plant process and / or ineffective operation of the plant process.

[0004] There are two main reasons for such erroneous sensor information and / or sensor readings. The first reason is the sensor device itself, such as a damaged sensing element within the sensor device, like a pH membrane or humidity sensor, or a fault in the communication chain used to transmit sensor information to the control unit. This fault can be identified and reported by the sensor device, for example, through its internal self-test. Therefore, calibration measures, such as replacing the sensor device, can be taken.

[0005] The second reason is that the sensor readings of the sensed parameters slowly deviate from the actual values ​​of those parameters, even though the sensor device indicates it is fully functional. This phenomenon is called "drift sensor readings" and can be caused, for example, by contamination or wear of the sensing device, particularly the sensing element. To avoid sensor reading drift, the sensor device is typically compared to laboratory results from samples collected near the sensor device's measurement point. If a deviation is identified between the laboratory results and the sensor information / sensor readings, the sensor device is calibrated. This procedure is usually performed at given (time) intervals, such as weekly, bi-weekly, or every X operating hours. However, interval-based comparisons / calibrations of sensor devices are cumbersome and time-consuming / resource-intensive. Furthermore, drift sensor readings occurring between successive sensor device comparisons / calibrations may go undetected and could lead to inappropriate control actions in control systems that rely on sensor information. Summary of the Invention

[0006] Therefore, the object of the present invention is to improve the detection of faulty sensor readings / information and / or sensor device readings, particularly drift sensor readings, to ensure that plant processes can operate efficiently while ensuring compliance.

[0007] These and other objectives of the present invention are achieved by means of the following aspects.

[0008] The first aspect relates to a method for verifying the reliability of sensor information sensed by a sensor device associated with a plant process, particularly a water treatment process and / or a wastewater treatment process, wherein the sensor information is related to the plant process, the method comprising:

[0009] The sensor information is received by the control unit;

[0010] The control unit executes a verification model that determines the expected sensor information that the sensor device should provide, wherein the verification model determines the expected sensor information based on at least one other piece of information that is related to the plant process and has a relation to the sensor information;

[0011] Compare the expected sensor information with the received sensor information; and

[0012] When it is determined that the sensor information deviates from the expected sensor information, the control unit outputs a verification signal.

[0013] Advantageously, this disclosure uses additional information relevant to the plant process to determine whether the sensor information related to the plant process is accurate and reliable. Therefore, sensor misreads can be detected even when the sensor device does not report any errors, such as errors from built-in self-tests, and appears to be operating normally. Furthermore, sensor misreads can be identified independently of the sensor device's comparison or calibration activities, depending on a given comparison or calibration interval. That is, this disclosure provides the possibility of performing event-based comparisons or calibrations on the sensor device. Specifically, if it is determined that the received sensor information differs from the expected sensor information, the output of a verification signal can initiate comparison or calibration activities for the sensor device.

[0014] Furthermore, because the validation model determines the expected sensor information based on at least one other piece of information related to the plant process, the desired sensor information is determined within the context of the (operating) plant process. That is, at least one piece of information and the sensor information can be correlated with each other, and the plant process and at least one piece of information can allow the expected sensor information to be derived. Additionally, at least one piece of information can be information that can be used to control and monitor the plant process and / or a phase of the plant process.

[0015] Sensor devices can provide sensor readings as sensor information for parameters related to the plant process. In other words, sensor information can be based on sensor readings of parameters related to the plant process. For example, sensor readings / information can represent oxygen concentration, nitrate concentration, phosphorus concentration, and / or residual chlorine related to the plant process. Further examples of sensor information and corresponding sensor devices involve water flow rate, air flow rate, chemical flow rate, pressure, valve position, and blower operating frequency.

[0016] In addition, the control unit can control the factory process based on sensor information. However, this does not necessarily mean that the control unit controls the factory process solely based on sensor information.

[0017] Furthermore, the control unit can use sensor information as feedback and / or feedforward parameters in plant process control. That is, the control unit can preferably continuously receive and / or evaluate sensor information and control the plant process in response to changes in the sensor information. For example, a sensor device can provide sensor information about the phosphorus concentration in (waste) water, and the control unit can determine the dosage of chemicals (e.g., precipitants) to be applied in the plant process to meet a specific phosphorus concentration based on said sensor information. Continuing with the example of phosphorus concentration, at least one other piece of information can be correlated with the dosage of chemicals already applied in the plant process. Based on this information, a validation model can determine how the phosphorus concentration, preferably continuously measured by the sensor device, should behave, i.e., how the phosphorus concentration should develop over time. In the event of inconsistency between the actual sensor readings / sensor information measured by the sensor device, the control unit can determine that the sensor information is unreliable and output a validation signal.

[0018] Preferably, at least one additional piece of information is not derived from the sensor device. For the purposes of this disclosure, the term "not derived" should be interpreted as instantaneous sensor readings and / or sensor information transmitted by the sensor device. Therefore, data models based on sensor information collected from the sensor device, such as those based on sensor information collected over a period of time, should not fall under the term "not derived." Where the sensor device supports sensor information / readings for more than one parameter (e.g., ammonia and nitrate concentrations), each individual piece of sensor information from the sensor device is considered to represent sensor information from a dedicated sensor device. That is, for the purposes of this disclosure, it is assumed that sensor information not corresponding to received sensor information (i.e., sensor information related to different parameters of the plant process) can be used for at least one additional piece of information. Furthermore, for the purposes of this disclosure, it is assumed that information related to the internal functions of the sensor device (e.g., built-in or internal self-tests of the sensor device) does not represent at least one additional piece of information because it is unrelated to the plant process. Instead, such information is related to the internal operation of the sensor device.

[0019] Preferably, at least one of the following is: second sensor information of a second sensor device associated with the plant process, process parameters associated with the plant process, plant process constraints, and control activities associated with the plant process. Advantageously, the reliability of the sensor information can therefore be verified based on plant process-related information.

[0020] For example, a second sensor device can provide sensor readings related to the dosage of chemicals applied during the plant process as second sensor information. Based on this dosage information, a validation model can determine the expected sensor information that the sensor device (first sensor device) should provide / communicate, since the dosage of chemicals applied during the plant process may have a deterministic effect on the parameters read by the first sensor device.

[0021] Additionally, process parameters, as at least one piece of other information, can provide a time-based relationship between at least one piece of other information and sensor information. For example, process parameters could be consumption information from past periods, such as energy consumed for aeration and / or chemicals consumed at a specific time of day. Furthermore, if it is determined that the consumption determined based on sensor information deviates from past consumption information, a verification signal is output. The verification signal can further indicate that the sensor device may be faulty and / or that the sensor device sensing the process parameter that influences the process parameter associated with at least one piece of other information (i.e., energy consumption or chemical consumption for aeration) is faulty. For example, if the current energy consumption for aeration deviates from the expected energy consumption, the sensor device used in closed-loop control to sense oxygen and / or ammonium concentrations may be faulty, leading to inappropriate aeration control.

[0022] Additionally, plant process constraints, as at least one other piece of information, can provide a framework for defining the relationship between plant process limitations and sensor information. Plant process constraints can be physical and / or chemical constraints imposed by the plant process itself, such as those imposed by the physical layout of the plant operating the process. For example, sensor information related to sensor readings of flow rate or flow rate variations in the plant's hydraulic system can be compared to expected flow rate or flow rate variations based on plant process constraints. As an example of such constraints, reactor volume, flow rate to the reactor, and assumed maximum inflow concentration can be considered, leading to the expected maximum variation in sensor readings of the sensor device. Therefore, a deviation between the expected flow rate and the measured flow rate (current sensor information) may result in an output verification signal. The verification signal can indicate a potential malfunction in the sensor device transmitting the sensor information.

[0023] Additionally, control activities related to the plant process, as at least one other source of information, can provide details about the relationship between the control activities and the sensor information. Control activities may involve modifying control parameters or parameters of the plant process that affect it. For example, increasing aeration energy in the plant process should result in a decrease in the ammonium (NH4-N) sensor reading on the sensor device. Therefore, if the current sensor reading does not decrease, a verification signal can be output. The verification signal can further indicate that the sensor device transmitting the sensor information may be faulty.

[0024] Preferably, the verification model includes at least one rule for determining expected sensor information based on at least one other piece of information. Therefore, at least one rule defines the relationship or dependency between at least one piece of other information and the sensor information. If the expected sensor information deviates from the sensor information, the control unit can assume a violation of at least one rule, which may result in an output verification signal. Furthermore, the at least one rule can be deterministic. That is, the same input to the rule provides the same output, i.e., the same expected sensor information. Moreover, the rules can be correlated with each other, thereby allowing for fine-grained determination of the expected sensor information. Therefore, if one or more, or even all, of the relevant rules are violated, a verification signal can be output.

[0025] In addition, at least one rule can further define the verification information to be released along with the verification signal. The verification information can indicate a potentially faulty sensor device. This is particularly useful when a rule violates a provision indicating a fault in a sensor device other than the one providing sensor information for comparison with the expected sensor information.

[0026] Furthermore, at least one rule can be defined by the user. For example, the control unit can provide a user interface that allows defining at least one rule.

[0027] Preferably, at least one rule is based on historical data related to the factory process or determined during a learning cycle. For example, at least one rule may be determined by an artificial intelligence module trained with historical data.

[0028] Preferably, the method may include: switching the control unit to a safety control mode for controlling the plant process in response to a verification signal. Therefore, safety control of the plant process can be provided in the event of incorrect operation of the sensor devices. Additionally, one or more control mode activities for the safety control mode may be defined and / or provided with verification signals in the control unit. For the latter, at least one rule may be associated with one or more control mode activities; and, in the event of a rule violation, the corresponding one or more control mode activities are output along with the verification signal. Furthermore, one or more control mode activities may preferably be applied to the plant process via the control unit. For example, one or more control mode activities may result in the plant process being executed at a reduced level.

[0029] Preferably, the method may include: initiating a maintenance procedure for the sensor device, particularly a comparison / calibration procedure, in response to a verification signal. The comparison / calibration procedure may be automatic or may be performed manually, for example, by an operator. In the latter case, the output of the verification signal may result in a notification being sent to the operator that the sensor device may be faulty or that the sensor reading may be faulty and requires calibration. The notification may be transmitted to the operator by a control unit, such as a computing device.

[0030] Furthermore, after completing automatic and / or manual comparison / calibration, if laboratory measurements confirm the process readings, the control unit can switch from safety control mode back to normal control mode. Calibration completion can be notified to the control unit electronically.

[0031] Preferably, the expected sensor information specifies a range of parameter values, and a verification signal is output when the sensor information falls outside said range. Furthermore, the expected sensor information may specify the behavior of the sensor information / sensor device. For example, the behavior may be an increase or decrease in sensor readings over time. Additionally, changes in sensor readings may be considered sensor information and / or at least one other type of information.

[0032] On the other hand, a control unit for controlling a plant process, particularly a water treatment process and / or wastewater treatment process, is disclosed. The control unit is communicatively coupled to a sensor device associated with and sensing sensor information related to the plant process. The control unit is configured to:

[0033] Receive the sensor information;

[0034] A verification model is executed to determine the expected sensor information of the sensor device based on at least one other piece of information that is related to the plant process and has a relation to the sensor information;

[0035] Compare the expected sensor information with the received sensor information; and

[0036] A verification signal is output when it is determined that the sensor information deviates from the expected sensor information.

[0037] The control unit can be implemented in hardware or provided as software for execution on a computing device.

[0038] Furthermore, the control unit may have the features described in the foregoing aspects.

[0039] On the other hand, it may involve a computer program product including instructions that, when executed by a control unit for controlling a plant process, particularly a water treatment process and / or a wastewater treatment process, cause the control unit to perform the method according to the foregoing aspects, wherein the control unit is communicatively coupled to a sensor device associated with the plant process and senses sensor information related to the plant process. Attached Figure Description

[0040] These and other objects, features, and advantages of the invention will become more apparent from the following detailed description of preferred embodiments and accompanying drawings. It should be understood that even though embodiments are described separately, their individual features can be combined into additional embodiments.

[0041] Figure 1 Methods for verifying the reliability of sensor information during factory processes are described, and

[0042] Figure 2 The process of defining at least one rule for the validation model is described. Detailed Implementation

[0043] Figure 1 A method for verifying the reliability of sensor information in a plant process (e.g., a (waste)water treatment process) is schematically depicted. Some of the steps in the depicted method may be optional and are depicted to provide a better understanding of the context of this disclosure. The method is described as a closed loop because it is performed continuously during the execution of the plant process.

[0044] Plant processes can be controlled based on data / information related to the plant processes, particularly sensor information / readings. Sensor information can be based on sensor readings. For example, one or more sensor devices can provide plant process-related sensor information to a control unit, which then performs one or more control activities based on this sensor information. Sensor information can represent values ​​of process parameters of the plant process.

[0045] The sensor device can be a process analyzer and / or a process probe, which preferably continuously measures / reads parameters related to the plant process, such as oxygen concentration, nitrate concentration, etc. The sensor device can also be a non-analytical sensor, such as a water flow sensor, air flow sensor, or pressure sensor. Both process analyzers and non-analytical sensors can provide corresponding sensor information, which the control unit can use to control the plant process.

[0046] exist Figure 1 In step S100, sensor information from one or more sensor devices can be received. Optionally, the sensor information can be stored to provide historical data. Furthermore, the sensor information can be received by a control unit.

[0047] Additionally, the control unit can be configured to perform a verification model, wherein the verification allows for the determination of expected sensor information for one or more sensor devices based on at least one other piece of information related to the plant process and relating to the sensor information of the sensor devices. That is, the expected sensor information is determined based on the context of the plant process—the operation of the sensor devices within that process.

[0048] In step S110, the control unit executes a verification model to determine the expected sensor information.

[0049] Furthermore, in step S120, the determined expected sensor information is compared with the actual sensor information received by the sensor device to be verified. If the actual sensor information matches the expected sensor information, the factory process continues as is. That is, no abnormal control activities are performed.

[0050] When it is determined that the actual sensor information deviates from the expected sensor information, in step S130, the control unit outputs a verification signal. Based on the output of the verification signal in step S130, the control unit can switch to a rollback operation mode for controlling the plant process. Figure 1 (Step S140 in the text). The rollback operation mode can provide safe operation of the plant process, and it can be based on a control strategy that does not rely on fault sensor devices. In addition, the verification signal can include information about specific rollback control activities that will be performed by the control unit and / or the plant running the plant process.

[0051] Furthermore, in step S150, the control unit can initiate maintenance activities for the sensor device, such as comparison / calibration activities. For example, the control unit can automatically activate the sensor device's workflow process comparison / calibration, and / or can electronically transmit the need for comparison / calibration of the sensor device to the operator. For this purpose, the control unit, sensor device, and calibration facility can communicate and connect with each other, for example, via a cloud application. Additionally, a verification signal can indicate to the sensor(s)(s) for which maintenance activities should be performed.

[0052] In the first step of the comparison / calibration activity, the sensor information / sensor readings are compared with laboratory readings of a sample, preferably collected at the location of the sensor device. In the second step, it is determined whether the sensor readings match the laboratory readings. If the two readings do not match, the sensor device is calibrated and / or repaired and / or replaced, and the control unit is indicated that the maintenance activity is complete. If the two readings match, the maintenance activity is also indicated to be complete.

[0053] After completing the maintenance activities of the sensor device, in step S170, the control unit may switch back to the normal operating mode for controlling the plant process, provided that the control unit and / or the plant process are operating in the rollback mode (step S160).

[0054] The following sections discuss examples of at least one other piece of information upon which the verification is based in more detail.

[0055] Preferably, at least one of the following is: second sensor information of a second sensor device associated with the plant process, process parameters associated with the plant process, plant process constraints, and control activities associated with the plant process.

[0056] For example, a second sensor device can provide sensor readings related to the dosage of chemicals applied in the plant process as second sensor information. Based on this dosage information, a validation model can determine the expected sensor information that the sensor device (first sensor device) should provide / communicate, since the dosage of chemicals applied in the plant process can have a deterministic effect on the parameters read by the first sensor device. Furthermore, the dosage information can be correlated with the time of day and the stage of the plant process. In another example, sensor information from similar sensor devices in parallel processes / processing channels is compared. In yet another example, conductivity sensor readings can be used to validate sensor information / sensor readings from an NH4-N sensor.

[0057] Additionally, process parameters, as at least one piece of additional information, can provide a time-based relationship between at least one piece of additional information and sensor information. Specifically, historical data for a given time of day can be at least one piece of additional information. For example, process parameters can be consumption information from past periods, such as energy consumed and / or chemicals consumed for aeration. Furthermore, if typical consumption information determined based on sensor information deviates from past periods (e.g., at the same time of day), a verification signal is output. The verification signal can further indicate that the sensor device may be faulty and / or that the sensor device sensing the process parameter (i.e., energy consumption or chemical consumption for aeration) that affects that process parameter is faulty. For example, if the current energy consumption for aeration deviates from the expected energy consumption, the sensor device sensing the oxygen and / or ammonium concentration may be faulty, leading to inappropriate aeration control.

[0058] As a further example, process parameters could be historical data related to the consumption of chemicals (e.g., precipitants) at similar flow rates, which are also associated with sensor information.

[0059] Additionally, plant process constraints, as at least one other piece of information, can provide a framework for defining the relationship between plant process limitations and sensor information. Plant process constraints can be physical and / or chemical constraints imposed by the plant process itself, such as constraints imposed by the physical layout of the plant operating the process. For example, sensor information related to sensor readings of flow rate or flow rate changes in the plant's hydraulic system can be compared to expected flow rate or flow rate changes based on the plant's physical layout. Therefore, a deviation between the expected flow rate and the measured flow rate (current sensor information) may result in an output verification signal. This verification signal can indicate a potential malfunction in the sensor device transmitting the sensor information.

[0060] Additionally, control activities related to the plant process, as at least one other piece of information, can provide context for defining the relationship between the control activities and the sensor information. Control activities may involve modifying control parameters or parameters of the plant process that affect it. For example, increasing the aeration energy in the plant process as a control activity should result in a decrease in the ammonium (NH4-N) sensor reading on the sensor device. Therefore, if the current sensor reading does not decrease, a verification signal can be output. The verification signal can further indicate that the sensor device transmitting the sensor information may be faulty.

[0061] As a further example, at least one other piece of information may be related to airflow demand in certain areas / stages of a plant process (e.g., a wastewater treatment process), and this information is compared with corresponding sensor information. Therefore, a change in the ratio between these airflow demands may be caused by the sensor device reading the NH4-N concentration. Specifically, if multiple sensor devices are implemented in a closed-loop control structure, a drift of the NH4-N sensor reading to a higher reading will result in a higher air demand in the corresponding lane. Furthermore, at least one other piece of information and sensor information may be related to a specific time of day.

[0062] As a further example, on intermittently operating equipment, when the process is controlled to be in the aeration phase, a sensor device reading the NH4-N parameter is expected to transmit 0 mg / L (expected sensor information) after a certain aeration time. If the actual sensor information deviates from the expected sensor information, a verification signal is output to initiate maintenance activities for the sensor device.

[0063] Preferably, the verification model includes at least one rule for determining expected sensor information based on at least one other piece of information. Therefore, the at least one rule defines the relationship or dependency between the at least one other piece of information and the sensor information. If the expected sensor information deviates from the sensor information, the control unit can assume a violation of at least one rule, which may result in an output verification signal. Furthermore, the at least one rule can be deterministic. That is, the same input to the rule provides the same output, i.e., the same expected sensor information. Moreover, the rules can be correlated with each other, thereby allowing for fine-grained determination of the expected sensor information. Therefore, if all relevant rules are violated, a verification signal can be output.

[0064] In addition, at least one rule can further define the verification information to be released along with the verification signal. The verification information can indicate a potentially faulty sensor device. This is particularly useful when a rule violates a provision indicating a fault in a sensor device other than the one providing sensor information for comparison with the expected sensor information.

[0065] Furthermore, at least one rule can be defined by the user. For example, the control unit can provide a user interface that allows defining at least one rule.

[0066] Preferably, at least one rule is based on historical data related to the factory process or determined during a learning cycle (see step S100). For example, at least one rule may be determined by an artificial intelligence module trained with historical data.

[0067] refer to Figure 2 The process of defining at least one rule for the verification model is described in more detail. In step S210, one or more deterministic rules may be defined. The deterministic rules may be based on the relationship between sensor information and at least one other piece of information. The deterministic rules may be defined by the user and stored in the control unit.

[0068] Alternatively or additionally, one or more empirical rules may be defined. Empirical rules may be defined during the learning period and / or based on historical dates. For example, historical data stored in step S100 or other previously stored historical information.

[0069] In step S220, sensor devices and / or signals are defined for monitoring during subsequent empirical relationship evaluation. In step S230, the correlation of the defined sensor devices and / or signals is examined based on an evaluation that may be based on historical data. If a correlation has been found between sensor devices and / or signals, a corresponding empirical rule is defined in step S240, wherein the rule defines the relationship between sensor devices and / or signals related to the plant process. The process generates at least one defined rule. The at least one rule can be applied to validate the model.

[0070] Further features, characteristics, and advantages of the invention will be described below by way of the following clauses:

[0071] 1. A method for verifying the reliability of sensor information sensed by a sensor device associated with a plant process, particularly a water treatment process and / or a wastewater treatment process, wherein the sensor information is related to the plant process, the method comprising:

[0072] The sensor information is received by the control unit;

[0073] The control unit executes a verification model that determines the expected sensor information that the sensor device should provide, wherein the verification model determines the expected sensor information based on at least one other piece of information that is related to the plant process and has a relation to the sensor information;

[0074] Compare the expected sensor information with the received sensor information; and

[0075] When it is determined that the sensor information deviates from the expected sensor information, the control unit outputs a verification signal.

[0076] 2. The method as described in item 1, wherein the at least one other piece of information is not derived from the sensor device.

[0077] 3. The method as described in clause 1 or 2, wherein the at least one other piece of information is at least one of the following: second sensor information of a second sensor device associated with the plant process, process parameters associated with the plant process, plant process constraints, and control activities associated with the plant process.

[0078] 4. The method of any one of clauses 1 to 3, wherein the verification model includes at least one rule for determining the expected sensor information based on the at least one other piece of information.

[0079] 5. The method as described in item 4, wherein the at least one rule is determined based on historical data related to the plant process.

[0080] 6. The method according to any one of the preceding clauses further includes:

[0081] In response to the verification signal, the control unit is switched to a safety control mode for controlling the plant process.

[0082] 7. The method according to any one of the preceding clauses further includes:

[0083] In response to the verification signal, a maintenance procedure for the sensor device is initiated, particularly a comparison / calibration procedure.

[0084] 8. The method described in item 6 further includes:

[0085] In response to the verification signal, a maintenance procedure for the sensor device is initiated, particularly a comparison / calibration procedure; and

[0086] After completing the maintenance procedure, the control unit is switched from safety control mode back to normal control mode.

[0087] 9. A control unit for controlling a plant process, particularly a water treatment process and / or a wastewater treatment process, the control unit being communicatively coupled to a sensor device associated with the plant process and sensing sensor information related to the plant process, the control unit being configured to:

[0088] Receive the sensor information;

[0089] A verification model is executed to determine the expected sensor information that the sensor device should provide, wherein the verification model determines the expected sensor information based on at least one other piece of information that is related to the plant process and has a relation to the sensor information;

[0090] Compare the expected sensor information with the received sensor information; and

[0091] A verification signal is output when it is determined that the sensor information deviates from the expected sensor information.

[0092] 10. The control unit as described in item 9, wherein the at least one other piece of information is not derived from the sensor device; and / or

[0093] The at least one other piece of information is at least one of the following: second sensor information of a second sensor device associated with the plant process, process parameters associated with the plant process, plant process constraints, and control activities associated with the plant process.

[0094] 11. The control unit as described in item 9 or 10, wherein the verification model includes at least one rule for determining the expected sensor information based on the at least one other piece of information.

[0095] 12. The control unit as described in clause 11, wherein the at least one rule is determined based on historical data related to the plant process.

[0096] 13. The control unit as described in any one of clauses 9 to 12, wherein the control unit is configured to switch to a safety control mode for controlling the plant process in response to the verification signal.

[0097] 14. The control unit as described in clause 13, wherein the control unit is further configured to: initiate a maintenance procedure for the sensor device, particularly a comparison / calibration procedure, and switch from the safety control mode to the normal control mode of the plant process after receiving an indication that the maintenance procedure has been completed.

[0098] 15. A computer program product comprising instructions that, when executed by a control unit for controlling a plant process, particularly a water treatment process and / or a wastewater treatment process, cause the control unit to perform the method as described in any one of clauses 1 to 8, the control unit being communicatively coupled to a sensor device associated with the plant process and sensing sensor information related to the plant process.

Claims

1. A method for verifying the reliability of sensor information sensed by a sensor device associated with a factory process, wherein, The sensor information is related to the factory process, and the method includes: receiving the sensor information by a control unit; characterized in that the method further includes: The control unit executes a verification model that determines the expected sensor information that the sensor device should provide. The verification model determines the expected sensor information based on at least one other piece of information related to the plant process and relating to the sensor information. This at least one other piece of information is at least one of the following: process parameters related to the plant process, plant process constraints, and control activities related to the plant process. The verification model includes at least one rule for determining the expected sensor information based on the at least one other piece of information, the at least one rule defining the relationship or dependency between the at least one other piece of information and the sensor information. Compare the expected sensor information with the received sensor information; and When it is determined that the sensor information deviates from the expected sensor information, the control unit outputs a verification signal.

2. The method as described in claim 1, wherein, The plant process is a water treatment process and / or a wastewater treatment process.

3. The method as described in claim 1 or 2, wherein, The at least one other piece of information is not derived from the sensor device.

4. The method as described in claim 1 or 2, wherein, The at least one rule is determined based on historical data related to the plant process.

5. The method of claim 1 or 2, further comprising: In response to the verification signal, the control unit is switched to a safety control mode for controlling the plant process.

6. The method of claim 1 or 2, further comprising: In response to the verification signal, a maintenance procedure for the sensor device is initiated.

7. The method of claim 6, wherein, The maintenance procedure is a comparison / calibration procedure.

8. The method of claim 5, further comprising: In response to the verification signal, a maintenance procedure for the sensor device is initiated; as well as After completing the maintenance procedure, the control unit is switched from safety control mode back to normal control mode.

9. The method of claim 8, wherein, The maintenance procedure is a comparison / calibration procedure.

10. A control unit for controlling a factory process, the control unit being communicatively coupled to a sensor device associated with and sensing sensor information related to the factory process, the control unit being configured to: receive the sensor information; characterized in that, The control unit is configured to: A verification model is executed to determine the expected sensor information that the sensor device should provide, wherein the verification model determines the expected sensor information based on at least one other piece of information that is related to the plant process and has a relationship with the sensor information, the at least one other piece of information being at least one of the following: process parameters related to the plant process, plant process constraints, and control activities related to the plant process, and the verification model includes at least one rule for determining the expected sensor information based on the at least one other piece of information, the at least one rule defining the relationship or dependency between the at least one other piece of information and the sensor information; Compare the expected sensor information with the received sensor information; and A verification signal is output when it is determined that the sensor information deviates from the expected sensor information.

11. The control unit as claimed in claim 10, wherein, The plant process is a water treatment process and / or a wastewater treatment process.

12. The control unit as claimed in claim 10 or 11, wherein, The at least one other piece of information is not derived from the sensor device.

13. The control unit as claimed in claim 10 or 11, wherein, The at least one rule is determined based on historical data related to the plant process.

14. The control unit as claimed in claim 10 or 11, wherein, The control unit is configured to switch to a safety control mode for controlling the plant process in response to the verification signal.

15. The control unit as claimed in claim 14, wherein, The control unit is further configured to: initiate a maintenance procedure for the sensor device, and switch from the safety control mode to the normal control mode of the plant process after receiving an indication that the maintenance procedure has been completed.

16. The control unit as claimed in claim 15, wherein, The maintenance procedure is a comparison / calibration procedure.

17. A computer program product comprising instructions that, when executed by a control unit for controlling a plant process, cause the control unit to perform the method as claimed in any one of claims 1 to 9, the control unit being communicatively coupled to a sensor device associated with the plant process and sensing sensor information related to the plant process.

18. The computer program product of claim 17, wherein, The plant process is a water treatment process and / or a wastewater treatment process.

Images