Predictive maintenance technology is increasingly influencing maintenance strategies and product development for industries across the world. As this technology continues to develop, customers will soon expect all heat treatment furnaces to leverage the Internet of Things (IoT) to perform such analysis.
For instance, with predictive maintenance technology, furnaces could be able to answer the 'what ifs', including:
- When a vacuum pump rebuild is going to be necessary
- When it isn't operating correctly
- When the user is at risk of experiencing discoloration in the next cycle
- When there is a heating element failure
Figure 1. This chart displays the progression of equipment as it becomes increasingly integrated with the Internet of Things. "Service" represents the capabilities of a traditional heat treatment furnace, while "Analyze" represents a heat treatment furnace integrated with predictive maintenance (courtesy of PTC).
Up until now, when a heat treatment furnace breaks the result is obvious: production comes to a halt and the personnel responsible for resolving the issue might not be readily available.
This results in companies experiencing unplanned downtime until the issue is resolved, in addition to the cost of rushing critical part shipments and potential overtime wages for the required personnel.
In order to deal with this issue, the key objective of predictive maintenance and Ipsen's PdMetrics® software platform for predictive maintenance is to execute maintenance at a fixed time when the maintenance activity is most cost-effective and before the performance of the equipment decreases below the set threshold.
Predicting when maintenance is required and preventing failures before they take place holds a number of benefits: including increasing furnace reliability and uptime, preventing high-cost events, minimizing the maintenance burden placed on shop personnel by unexpected downtime, and reducing the need for frequent maintenance/repair.
The addition of predictive maintenance also results in a smart, connected furnace that monitors in-service equipment to capture data that helps improve furnace operations and report when service is required. Predictive maintenance software, through analysis of the critical furnace data, can also detect deteriorating conditions, maintenance trends, and more.
This information allows furnace users to plan ahead – whether that means ensuring the necessary furnace parts are in stock or scheduling the necessary personnel to carry out maintenance. Data on the overall performance of the furnace can be gathered by furnace manufacturers that use predictive maintenance.
The ideal maintenance program integrates a well-balanced combination of predictive, corrective, and preventative maintenance in order to maintain the equipment in the best manner possible. However, it is the introduction of predictive maintenance that helps develop a cost-effective program that is capable of identifying failures before they occur, effectively preparing for any corrective maintenance that may be needed and scheduling maintenance as needed.
The applications of predictive maintenance will continue to expand as more and more equipment is developed to reduce unplanned downtime and optimize operations. By analyzing the emergence of predictive maintenance as a tool for investigating future performance and maintenance requirements – and also how Ipsen's PdMetrics® software platform is transforming the world of thermal processing – one can receive a better understanding of how companies can efficiently increase production and optimize operations while simultaneously reducing unplanned downtime and unnecessary costs.
The PdMetrics® Software Platform – Powerful but Simple Diagnostics
Proprietary sensors and control algorithms are used by the PdMetrics® software platform to establish the ideal time to service the furnace and replace parts. As soon as the software determines that an action is required, an automatic alert is sent to both Ipsen and the customer, notifying them in advance and facilitating the dispatch of service personnel or delivery of the required parts on a scheduled date.
Other main features include:
- Smart connectivity enables users to receive alerts through email and/or text message
- Furnace part replacement notifications based on usage and wear characteristics
- Stand-alone interface screen can integrate with several furnaces
- Technical support through via Ipsen's secure server enables Ipsen experts to quickly access the required data and extend optimum support
By tracking key parameters and critical data through the PdMetrics software platform, such as pressure, vibrations, and temperature, users can enhance the health and integrity of a number of systems: pumping system, hot zone, vacuum integrity, and cooling system (Figure 2).
Figure 2. The PdMetrics® software platform dashboard, where users can monitor the health and integrity of the hot zone, pumping system, cooling system, and vacuum integrity.
The Different Types of Maintenance
An analysis of the two common forms of maintenance currently used - corrective and preventative maintenance - sheds light on the emergence of predictive maintenance and its various benefits. All maintenance strategies have their own requirements and they are often carried out in conjunction with to another type of maintenance so as to maintain production levels, as well as to control maintenance costs (if not reduce them).
Corrective maintenance is seen as one of the most fundamental approaches to maintenance, and is normally used after a furnace fails to function correctly. Corrective maintenance often looks at the furnace's common symptoms to decide on the potential causes of failure and ultimately correct them.
While the performance of corrective maintenance keeps equipment up and running, it also has several inherent disadvantages, one being that it allows failures to occur. This results in an inevitable disruption to production, and it becomes both costly and difficult to reduce the time required to address the issue, as the user must always be prepared for something to go wrong.
Pat of this preperation includes having spare parts on hand at all times, having the storage space to keep the parts, paying overtime wages for maintenance personnel to correct the problem and more – all of which can result in low profitability.
Preventative maintenance involves regular maintenance and inspection of the furnace equipment prior to the occurrence of any major failures. A preventative maintenance (PM) program plays a major role in protecting equipment and generally encompasses regular repair, replacement, equipment servicing, and inspection. PM programs enable companies to schedule downtime in advance, and they also offer predictable annual maintenance costs.
Preventative maintenance is different from corrective maintenance, as instead of waiting for failures to occur before fixing them, it focuses on consistently preventing errors before they occur and keeping the furnace in exceptional working condition.
Thus, preventative maintenance is known to be an efficient technique for protecting equipment and preventing unplanned downtime. Time-based and condition-based maintenance are the two sub-categories of preventative maintenance.
Time-based maintenance can be defined as waiting for a particular trigger to occur before employing preventative action.
The trigger can be based on several items, such as production quantities, lead times, the amount of time passed, etc. A well known example of time-based maintenance is changing the oil in a car, as this particular action is executed at a fixed interval of time and/or according to a specific mileage.
However, time-based maintenance has its own disadvantages. For instance, low wear parts are exchanged on this time-based principle, which means that they will need to be replaced on a more frequent basis. Due to this, an increasing number of low wear parts must be bought and stored to prevent unnecessary downtime – all of which results in increased costs.
Overall, time-based maintenance is best used when the expenses it produces are lower than the costs that would occur during unscheduled downtime situations or the performance of another type of maintenance, such as corrective maintenance.
Condition-based maintenance, which is not too different from time-based maintenance, also relies on a trigger to indicate when preventative action is needed. Here, the trigger is the desired condition of the equipment.
Evaluated at regular, time-based intervals, wear-related conditions are recorded either through human inspection or with sensors and then compared against the necessary wear allowed for safe operation. When that value is exceeded, maintenance for the necessary systems and/or the necessary parts is needed.
One example of condition-based maintenance is the replacement of car tires when the minimum tread depth goes below the prescribed preset limit. Another example, when considering a heat treatment system, would be to adjust the pump water miser when the roughing pumps operating temperature goes outside the recommended limits.
However, this form of maintenance also has its own limitations. One being that if a limit is exceeded, it is immediately important to immediately execute maintenance. This results in unpredictable maintenance periods and also makes it necessary to always have a considerable amount of spare parts in stock – both of which result in increased storage costs and personnel.
Condition-based maintenance, just like time-based maintenance, is valuable when the expenses are reasonable with respect to the total benefits and also with regard to the cost of other kinds of maintenance.
Predictive maintenance aims at applying analytics to detect a risk of failure, thus enabling prevention of the failure before it even occurs. The ultimate predictive maintenance program is often used together with a preventative maintenance program, and is designed to schedule maintenance as required and prevent equipment failures.
Predictive maintenance also monitors the performance and other parameters of the furnace, and by doing this it provides significant data that can be examined for determining when maintenance is needed. This provides a heat treatment furnace that has the potential to perform what if scenarios.
This previously unutilized data can also be used to optimize the reliability, efficiency, performance, and various other parameters of the furnace. In a number of ways, predictive maintenance is considered to be an improved extension of the condition-based preventative maintenance system.
Predictive maintenance, compared to the other forms of maintenance, enables an all-encompassing planning of available resources, which helps minimize the need for unnecessary storage, personnel, and spare parts costs. Predictive maintenance also plays an efficient role in detecting problems that exist between scheduled inspections.
Generally, predictive maintenance systems carry a corresponding high benefit-to-cost factor, resulting in a customized solution for the most critical components of a larger system, which in this case, is a heat treatment furnace.
The Convergence of the Internet of Things and Big Data
Enhanced operation is one of the major driving forces behind the several decisions and actions made by various businesses. Demonstrating as much, the International Data Corporation (IDC) recently carried out a survey among operations and business professions that concluded: "the leading driver of Big Data and analytics projects is 'product or service improvement and innovation'".
By gaining insight into the convergence of Big Data and the IoT, one can better understand the increasing development of such projects.
Understanding the Internet of Things
In 1999, Kevin Ashton, then co-founder and executive director of the Auto-ID Center, first coined the term ‘Internet of Things’ in order to describe how physical objects are linked to the Internet:
Today computers – and, therefore, the Internet – are almost wholly dependent on human beings for information. Nearly all of the roughly 50 petabytes (a petabyte is 1,023 terabytes) of data available on the Internet were first captured and created by human beings – by typing, pressing a record button, taking a digital picture or scanning a bar code [...]
The problem is, people have limited time, attention and accuracy – all of which means they are not very good at capturing data about things in the real world [...]
If we had computers that knew everything there was to know about things – using data they gathered without any help from us – we would be able to track and count everything, and greatly reduce waste, loss and cost. We would know when things need replacing, repairing or recalling, and whether they were fresh or past their best.
Although the term IoT was coined in 1999, it was not until 2010 that the concept began to gain popularity.
The IoT is comprised of connections outside the industrial context, for instance wearable devices on people – meaning physical objects are connected through wireless and wired networks, e.g., a Fitbit that monitors varied aspects of one's health and records that data through a network connection.
Defining Big Data
If the IoT is approached as a multitude of Internet-connected sensors that are fixed to a range of 'things', then Big Data is regarded as a term for the huge amounts of data generated by these ‘things’. For example, if an individual carries a smartphone regularly, then all the frequent activities (within the phone and physical) will be tracked, analyzed, and acted upon. The data created by the smartphone activity is regarded as Big Data.
Four V's characterize Big Data: volume, velocity, variety, and veracity (i.e., accuracy). In other words, sensor-instrumented, connected industrial devices are rapidly yielding data (velocity), in huge amounts (volume), in a mixture of unstructured, semistructured or structured information (variety). This data can be noisy and of uneven quality (veracity), demonstrating that specific data can be more accurate than others based on its origin.
This data is subsequently applied in analytics initiatives, such as predictive maintenance, to discover "early signals that predict machine failure to determine priorities for asset maintenance or anticipate a shift in demand that impact an operations delivery capability." This in turn contributes to enhanced operations through predictive maintenance's utilization of Big Data and the IoT.
Development of the PdMetrics Software Platform
Ipsen developed the PdMetrics® software platform for companies to develop value from the massive amounts of data available from their equipment and processes running in the furnace. They can then cost-effectively and efficiently reduce unnecessary downtime while simultaneously optimizing operations.
PdMetrics provides users are provided with four primary features. These features include a Diagnostic Helper with access to important tools and resources, the ability to obtain maximum equipment performance, continuous optimization of furnace usage, and an intelligent maintenance routine. All of these features help develop an integrated user experience.
The ability to monitor critical data and significant furnace parameters is becoming a vital requirement as more and more companies focus on reducing machine failures and the associated maintenance costs. Industry studies have highlighted that failure of a machine critical to an operational process can have a huge impact on the revenue that a firm can generate.
Timely, accurate predictions can help to save millions of dollars in maintenance costs. The utilization of a software platform for predictive maintenance will help to provide solutions for all personnel levels, starting from the furnace operator, who can now effortlessly monitor the ongoing status and health of the furnace, to management, who can have a complete view of the overall operation through a network of linked furnaces with increased intelligence (Figure 3).
Figure 3. The above chart illustrates the degree to which having a connected furnace positively impacts different departments and aspects of a company's operations – from the furnace operator to management.
For example, consider how the four main features function when monitoring the critical data necessary for the hot zone:
Maximum Equipment Performance
Maximum performance of the hot zone is ensured by monitoring parameters such as heat loss, resistance to ground, hot zone cleanliness, and open circuits. This helps prevent arcing, which can cause damage to the heating elements, ensure accurate heating uniformity, and eliminate high-energy consumption by the hot zone.
The Diagnostic Helper provides an Ask the Expert feature and leak diagnostic procedures that assist furnace users with determining the cause of any problematic symptoms. A number of valuable resources, such as guidelines on maintenance troubleshooting, valve troubleshooting sequences, etc. are also provided by the Diagnostic Helper
For instance, if a furnace is experiencing difficulty attaining vacuum levels (i.e., evacuating), this can be indicitive of a leak. The Diagnostic Helper's resources can then be used to determine the main cause before the leak gradually degrades the hot zone. However, if experiencing outgassing, a lengthy pumpdown and/or dirty parts, users can use the weather station to see if the humidity levels are high enough to be the cause, or if these symptoms actually indicate a bigger issue.
Intelligent Maintenance Routine
While it is still important to have a set PM program and corrective maintenance capabilities, the PdMetrics software platform builds upon the currently available maintenance and PM programs by integrating an intelligent maintenance routine that offers automatic reminders based on component usage and furnace performance.
As a result, instead of replacing hot zone components or checking for discoloration based on how much time has passed, users are notified when the hot zone indicates the need for such maintenance. This then enables the scheduled allocation of resources toward replacement parts, maintenance personnel, and more.
In addition, whenever an action is needed and/or an anomaly is experienced by the furnace, a log of all the issues or errors ever experienced by the furnace will be maintained by the software platform.
Another intelligent maintenance capability of this software platform is its integration of calibration due dates. Consequently, it takes note of when calibration is required and provides sufficient time in advance to plan so that production can continue running without any hindrance.
Optimize Furnace Usage
Finally, users can consistently enhance their furnace usage, as well as experience increased operational visibility. The software platform's ability to integrate with multiple furnaces and the smart connectivity that permits users to receive alerts through email and/or text message, simplify the process of monitoring multiple furnaces within a single location (Figure 4) as well as multiple furnaces within different facilities. As a result, it connects factories globally in a way that was not possible before.
By inspecting the data gathered, users are now able to more successfully implement any required improvements or adjustments that will help improve and refine the performance of the equipment and also more effectively delegate resources (e.g., parts, personnel) according to overall requirements.
Figure 4. The PdMetrics® software platform dashboard allows users to monitor the health and performance of multiple furnaces at once. Whenever an action is required or an error is experienced by one of the furnaces, it is signified by a yellow caution or a red danger warning sign.
What if your furnace could tell you that it isn't operating correctly?
This simple yet impactful question is the driving force behind the continuous evolution of maintenance procedures and methods. This constant evolution is necessary to successfully optimize operations and increase production, while simultaneously reducing unplanned downtime and manufacturing costs. Predictive maintenance is one solution to this what if scenario, as well as the next step on the maintenance evolution path.
Proceeding toward this path, many companies are now learning that predictive maintenance analytical models can guide managers to improve their decisions on how to deploy assets and when to preserve them in order to ensure efficient, safe, and optimized operations.
What Ipsen is discovering is that the PdMetrics software platform meant for predictive maintenance offers a new, innovative answer for the thermal processing industry with its ability to guarantee maximum equipment performance through real-time monitoring of critical systems.
Advantages include predicting and scheduling service based on the operational history of the furnace; integrating the software platform with the current service department to improve the tracking and scheduling of regular preventative maintenance activities, and reducing unplanned downtime with the ability to establish inventory requirements in advance and correct problem areas before they become complicated.
In the end the PdMetrics® software platform is a significant example of how predictive maintenance is growing as a tool for examining maintenance needs and equipment performance, this software platform also demonstrates how Big Data and the IoT have started to impact the field of heat treatment.
This information has been sourced, reviewed and adapted from materials provided by Ipsen.
For more information on this source, please visit Ipsen.